Search Results for author: Angjoo Kanazawa

Found 88 papers, 45 papers with code

Eye, Robot: Learning to Look to Act with a BC-RL Perception-Action Loop

no code implementations12 Jun 2025 Justin Kerr, Kush Hari, Ethan Weber, Chung Min Kim, Brent Yi, Tyler Bonnen, Ken Goldberg, Angjoo Kanazawa

In this way, hand-eye coordination emerges as the eye looks towards regions which allow the hand to complete the task.

Segment Any Motion in Videos

no code implementations CVPR 2025 Nan Huang, Wenzhao Zheng, Chenfeng Xu, Kurt Keutzer, Shanghang Zhang, Angjoo Kanazawa, Qianqian Wang

Moving object segmentation is a crucial task for achieving a high-level understanding of visual scenes and has numerous downstream applications.

Optical Flow Estimation Segmentation +1

Fillerbuster: Multi-View Scene Completion for Casual Captures

no code implementations7 Feb 2025 Ethan Weber, Norman Müller, Yash Kant, Vasu Agrawal, Michael Zollhöfer, Angjoo Kanazawa, Christian Richardt

Our solution is to train a generative model that can consume a large context of input frames while generating unknown target views and recovering image poses when desired.

Decentralized Diffusion Models

no code implementations CVPR 2025 David McAllister, Matthew Tancik, Jiaming Song, Angjoo Kanazawa

We propose Decentralized Diffusion Models, a scalable framework for distributing diffusion model training across independent clusters or datacenters by eliminating the dependence on a centralized, high-bandwidth networking fabric.

MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos

no code implementations CVPR 2025 Zhengqi Li, Richard Tucker, Forrester Cole, Qianqian Wang, Linyi Jin, Vickie Ye, Angjoo Kanazawa, Aleksander Holynski, Noah Snavely

We present a system that allows for accurate, fast, and robust estimation of camera parameters and depth maps from casual monocular videos of dynamic scenes.

Depth Estimation

Reconstructing People, Places, and Cameras

1 code implementation CVPR 2025 Lea Müller, Hongsuk Choi, Anthony Zhang, Brent Yi, Jitendra Malik, Angjoo Kanazawa

We present "Humans and Structure from Motion" (HSfM), a method for jointly reconstructing multiple human meshes, scene point clouds, and camera parameters in a metric world coordinate system from a sparse set of uncalibrated multi-view images featuring people.

Camera Pose Estimation Pose Estimation

MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos

1 code implementation5 Dec 2024 Zhengqi Li, Richard Tucker, Forrester Cole, Qianqian Wang, Linyi Jin, Vickie Ye, Angjoo Kanazawa, Aleksander Holynski, Noah Snavely

We present a system that allows for accurate, fast, and robust estimation of camera parameters and depth maps from casual monocular videos of dynamic scenes.

Depth Estimation

SOAR: Self-Occluded Avatar Recovery from a Single Video In the Wild

no code implementations31 Oct 2024 Zhuoyang Pan, Angjoo Kanazawa, Hang Gao

SOAR leverages structural normal prior and generative diffusion prior to address such an ill-posed reconstruction problem.

Agent-to-Sim: Learning Interactive Behavior Models from Casual Longitudinal Videos

no code implementations21 Oct 2024 Gengshan Yang, Andrea Bajcsy, Shunsuke Saito, Angjoo Kanazawa

We present Agent-to-Sim (ATS), a framework for learning interactive behavior models of 3D agents from casual longitudinal video collections.

4D reconstruction

Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstruction

1 code implementation26 Sep 2024 Justin Kerr, Chung Min Kim, Mingxuan Wu, Brent Yi, Qianqian Wang, Ken Goldberg, Angjoo Kanazawa

This analysis-by-synthesis approach uses part-centric feature fields in an iterative optimization which enables the use of geometric regularizers to recover 3D motions from only a single video.

4D reconstruction Object +1

gsplat: An Open-Source Library for Gaussian Splatting

1 code implementation10 Sep 2024 Vickie Ye, RuiLong Li, Justin Kerr, Matias Turkulainen, Brent Yi, Zhuoyang Pan, Otto Seiskari, Jianbo Ye, Jeffrey Hu, Matthew Tancik, Angjoo Kanazawa

gsplat is an open-source library designed for training and developing Gaussian Splatting methods.

Synergy and Synchrony in Couple Dances

no code implementations6 Sep 2024 Vongani Maluleke, Lea Müller, Jathushan Rajasegaran, Georgios Pavlakos, Shiry Ginosar, Angjoo Kanazawa, Jitendra Malik

Our contributions are a demonstration of the advantages of socially conditioned future motion prediction and an in-the-wild, couple dance video dataset to enable future research in this direction.

motion prediction Prediction

Splatfacto-W: A Nerfstudio Implementation of Gaussian Splatting for Unconstrained Photo Collections

no code implementations17 Jul 2024 Congrong Xu, Justin Kerr, Angjoo Kanazawa

Novel view synthesis from unconstrained in-the-wild image collections remains a significant yet challenging task due to photometric variations and transient occluders that complicate accurate scene reconstruction.

3DGS NeRF +1

Rethinking Score Distillation as a Bridge Between Image Distributions

no code implementations13 Jun 2024 David McAllister, Songwei Ge, Jia-Bin Huang, David W. Jacobs, Alexei A. Efros, Aleksander Holynski, Angjoo Kanazawa

We compare our method to existing approaches for score distillation sampling and show that it can produce high-frequency details with realistic colors.

NeRF

NeRF-XL: Scaling NeRFs with Multiple GPUs

no code implementations24 Apr 2024 RuiLong Li, Sanja Fidler, Angjoo Kanazawa, Francis Williams

We present NeRF-XL, a principled method for distributing Neural Radiance Fields (NeRFs) across multiple GPUs, thus enabling the training and rendering of NeRFs with an arbitrarily large capacity.

NeRF

The More You See in 2D, the More You Perceive in 3D

1 code implementation4 Apr 2024 Xinyang Han, Zelin Gao, Angjoo Kanazawa, Shubham Goel, Yossi Gandelsman

Inspired by this behavior, we introduce SAP3D, a system for 3D reconstruction and novel view synthesis from an arbitrary number of unposed images.

3D Reconstruction Image to 3D +1

GARField: Group Anything with Radiance Fields

1 code implementation CVPR 2024 Chung Min Kim, Mingxuan Wu, Justin Kerr, Ken Goldberg, Matthew Tancik, Angjoo Kanazawa

We optimize this field from a set of 2D masks provided by Segment Anything (SAM) in a way that respects coarse-to-fine hierarchy, using scale to consistently fuse conflicting masks from different viewpoints.

Scene Understanding

From Audio to Photoreal Embodiment: Synthesizing Humans in Conversations

1 code implementation CVPR 2024 Evonne Ng, Javier Romero, Timur Bagautdinov, Shaojie Bai, Trevor Darrell, Angjoo Kanazawa, Alexander Richard

We present a framework for generating full-bodied photorealistic avatars that gesture according to the conversational dynamics of a dyadic interaction.

Diversity Quantization

The More You See in 2D the More You Perceive in 3D

1 code implementation CVPR 2024 Xinyang Han, Zelin Gao, Angjoo Kanazawa, Shubham Goel, Yossi Gandelsman

Inspired by this behavior we introduce SAP3D a system for 3D reconstruction and novel view synthesis from an arbitrary number of unposed images.

3D Reconstruction Image to 3D +1

NeRFiller: Completing Scenes via Generative 3D Inpainting

no code implementations CVPR 2024 Ethan Weber, Aleksander Hołyński, Varun Jampani, Saurabh Saxena, Noah Snavely, Abhishek Kar, Angjoo Kanazawa

In contrast to related works, we focus on completing scenes rather than deleting foreground objects, and our approach does not require tight 2D object masks or text.

3D Inpainting

Mathematical Supplement for the $\texttt{gsplat}$ Library

1 code implementation4 Dec 2023 Vickie Ye, Angjoo Kanazawa

This report provides the mathematical details of the gsplat library, a modular toolbox for efficient differentiable Gaussian splatting, as proposed by Kerbl et al.

State of the Art on Diffusion Models for Visual Computing

no code implementations11 Oct 2023 Ryan Po, Wang Yifan, Vladislav Golyanik, Kfir Aberman, Jonathan T. Barron, Amit H. Bermano, Eric Ryan Chan, Tali Dekel, Aleksander Holynski, Angjoo Kanazawa, C. Karen Liu, Lingjie Liu, Ben Mildenhall, Matthias Nießner, Björn Ommer, Christian Theobalt, Peter Wonka, Gordon Wetzstein

The field of visual computing is rapidly advancing due to the emergence of generative artificial intelligence (AI), which unlocks unprecedented capabilities for the generation, editing, and reconstruction of images, videos, and 3D scenes.

Language Embedded Radiance Fields for Zero-Shot Task-Oriented Grasping

no code implementations14 Sep 2023 Adam Rashid, Satvik Sharma, Chung Min Kim, Justin Kerr, Lawrence Chen, Angjoo Kanazawa, Ken Goldberg

Instead, we propose LERF-TOGO, Language Embedded Radiance Fields for Task-Oriented Grasping of Objects, which uses vision-language models zero-shot to output a grasp distribution over an object given a natural language query.

Object

Can Language Models Learn to Listen?

no code implementations ICCV 2023 Evonne Ng, Sanjay Subramanian, Dan Klein, Angjoo Kanazawa, Trevor Darrell, Shiry Ginosar

We present a framework for generating appropriate facial responses from a listener in dyadic social interactions based on the speaker's words.

Language Modeling Language Modelling +1

Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives

no code implementations NeurIPS 2023 Tom Monnier, Jake Austin, Angjoo Kanazawa, Alexei A. Efros, Mathieu Aubry

We compare our approach to the state of the art on diverse scenes from DTU, and demonstrate its robustness on real-life captures from BlendedMVS and Nerfstudio.

Physical Simulations

Generative Proxemics: A Prior for 3D Social Interaction from Images

1 code implementation CVPR 2024 Lea Müller, Vickie Ye, Georgios Pavlakos, Michael Black, Angjoo Kanazawa

To address this, we present a novel approach that learns a prior over the 3D proxemics two people in close social interaction and demonstrate its use for single-view 3D reconstruction.

3D Reconstruction Denoising +1

NerfAcc: Efficient Sampling Accelerates NeRFs

no code implementations ICCV 2023 RuiLong Li, Hang Gao, Matthew Tancik, Angjoo Kanazawa

Optimizing and rendering Neural Radiance Fields is computationally expensive due to the vast number of samples required by volume rendering.

NeRF

Nerfbusters: Removing Ghostly Artifacts from Casually Captured NeRFs

1 code implementation ICCV 2023 Frederik Warburg, Ethan Weber, Matthew Tancik, Aleksander Holynski, Angjoo Kanazawa

Casually captured Neural Radiance Fields (NeRFs) suffer from artifacts such as floaters or flawed geometry when rendered outside the camera trajectory.

NeRF Novel View Synthesis

Generating Continual Human Motion in Diverse 3D Scenes

no code implementations4 Apr 2023 Aymen Mir, Xavier Puig, Angjoo Kanazawa, Gerard Pons-Moll

We decompose the continual motion synthesis problem into walking along paths and transitioning in and out of the actions specified by the keypoints, which enables long generation of motions that satisfy scene constraints without explicitly incorporating scene information.

Motion Synthesis Navigate

LERF: Language Embedded Radiance Fields

5 code implementations ICCV 2023 Justin Kerr, Chung Min Kim, Ken Goldberg, Angjoo Kanazawa, Matthew Tancik

Humans describe the physical world using natural language to refer to specific 3D locations based on a vast range of properties: visual appearance, semantics, abstract associations, or actionable affordances.

NeRF

Decoupling Human and Camera Motion from Videos in the Wild

1 code implementation CVPR 2023 Vickie Ye, Georgios Pavlakos, Jitendra Malik, Angjoo Kanazawa

Our method robustly recovers the global 3D trajectories of people in challenging in-the-wild videos, such as PoseTrack.

NerfAcc: A General NeRF Acceleration Toolbox

1 code implementation10 Oct 2022 RuiLong Li, Matthew Tancik, Angjoo Kanazawa

We propose NerfAcc, a toolbox for efficient volumetric rendering of radiance fields.

NeRF

Studying Bias in GANs through the Lens of Race

no code implementations6 Sep 2022 Vongani H. Maluleke, Neerja Thakkar, Tim Brooks, Ethan Weber, Trevor Darrell, Alexei A. Efros, Angjoo Kanazawa, Devin Guillory

In this work, we study how the performance and evaluation of generative image models are impacted by the racial composition of their training datasets.

The One Where They Reconstructed 3D Humans and Environments in TV Shows

no code implementations28 Jul 2022 Georgios Pavlakos, Ethan Weber, Matthew Tancik, Angjoo Kanazawa

TV shows depict a wide variety of human behaviors and have been studied extensively for their potential to be a rich source of data for many applications.

3D Reconstruction Gaze Estimation

InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images

1 code implementation22 Jul 2022 Zhengqi Li, Qianqian Wang, Noah Snavely, Angjoo Kanazawa

We present a method for learning to generate unbounded flythrough videos of natural scenes starting from a single view, where this capability is learned from a collection of single photographs, without requiring camera poses or even multiple views of each scene.

Perpetual View Generation

Domain Adaptive 3D Pose Augmentation for In-the-wild Human Mesh Recovery

1 code implementation21 Jun 2022 Zhenzhen Weng, Kuan-Chieh Wang, Angjoo Kanazawa, Serena Yeung

The ability to perceive 3D human bodies from a single image has a multitude of applications ranging from entertainment and robotics to neuroscience and healthcare.

Data Augmentation Domain Adaptation +1

TAVA: Template-free Animatable Volumetric Actors

1 code implementation17 Jun 2022 RuiLong Li, Julian Tanke, Minh Vo, Michael Zollhofer, Jurgen Gall, Angjoo Kanazawa, Christoph Lassner

Since TAVA does not require a body template, it is applicable to humans as well as other creatures such as animals.

Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion

no code implementations CVPR 2022 Evonne Ng, Hanbyul Joo, Liwen Hu, Hao Li, Trevor Darrell, Angjoo Kanazawa, Shiry Ginosar

We present a framework for modeling interactional communication in dyadic conversations: given multimodal inputs of a speaker, we autoregressively output multiple possibilities of corresponding listener motion.

Tracking People by Predicting 3D Appearance, Location and Pose

no code implementations CVPR 2022 Jathushan Rajasegaran, Georgios Pavlakos, Angjoo Kanazawa, Jitendra Malik

For a future frame, we compute the similarity between the predicted state of a tracklet and the single frame observations in a probabilistic manner.

Tracking People by Predicting 3D Appearance, Location & Pose

no code implementations8 Dec 2021 Jathushan Rajasegaran, Georgios Pavlakos, Angjoo Kanazawa, Jitendra Malik

For a future frame, we compute the similarity between the predicted state of a tracklet and the single frame observations in a probabilistic manner.

Tracking People with 3D Representations

1 code implementation NeurIPS 2021 Jathushan Rajasegaran, Georgios Pavlakos, Angjoo Kanazawa, Jitendra Malik

We find that 3D representations are more effective than 2D representations for tracking in these settings, and we obtain state-of-the-art performance.

3D geometry

Differentiable Gradient Sampling for Learning Implicit 3D Scene Reconstructions from a Single Image

no code implementations ICLR 2022 Shizhan Zhu, Sayna Ebrahimi, Angjoo Kanazawa, Trevor Darrell

Existing approaches for single object reconstruction impose supervision signals based on the loss of the signed distance value from all locations in a scene, posing difficulties when extending to real-world scenarios.

Indoor Scene Reconstruction Object Reconstruction +1

De-rendering the World's Revolutionary Artefacts

1 code implementation CVPR 2021 Shangzhe Wu, Ameesh Makadia, Jiajun Wu, Noah Snavely, Richard Tucker, Angjoo Kanazawa

Recent works have shown exciting results in unsupervised image de-rendering -- learning to decompose 3D shape, appearance, and lighting from single-image collections without explicit supervision.

AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control

4 code implementations5 Apr 2021 Xue Bin Peng, Ze Ma, Pieter Abbeel, Sergey Levine, Angjoo Kanazawa

Our system produces high-quality motions that are comparable to those achieved by state-of-the-art tracking-based techniques, while also being able to easily accommodate large datasets of unstructured motion clips.

Imitation Learning Reinforcement Learning (RL)

PlenOctrees for Real-time Rendering of Neural Radiance Fields

5 code implementations ICCV 2021 Alex Yu, RuiLong Li, Matthew Tancik, Hao Li, Ren Ng, Angjoo Kanazawa

We introduce a method to render Neural Radiance Fields (NeRFs) in real time using PlenOctrees, an octree-based 3D representation which supports view-dependent effects.

NeRF Neural Rendering +1

AI Choreographer: Music Conditioned 3D Dance Generation with AIST++

1 code implementation ICCV 2021 RuiLong Li, Shan Yang, David A. Ross, Angjoo Kanazawa

We present AIST++, a new multi-modal dataset of 3D dance motion and music, along with FACT, a Full-Attention Cross-modal Transformer network for generating 3D dance motion conditioned on music.

Motion Generation Motion Synthesis +1

Human Mesh Recovery from Multiple Shots

1 code implementation CVPR 2022 Georgios Pavlakos, Jitendra Malik, Angjoo Kanazawa

The tools we develop open the door to processing and analyzing in 3D content from a large library of edited media, which could be helpful for many downstream applications.

3D Reconstruction Human Mesh Recovery

Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image

1 code implementation ICCV 2021 Andrew Liu, Richard Tucker, Varun Jampani, Ameesh Makadia, Noah Snavely, Angjoo Kanazawa

We introduce the problem of perpetual view generation - long-range generation of novel views corresponding to an arbitrarily long camera trajectory given a single image.

Image Generation Perpetual View Generation +1

pixelNeRF: Neural Radiance Fields from One or Few Images

2 code implementations CVPR 2021 Alex Yu, Vickie Ye, Matthew Tancik, Angjoo Kanazawa

This allows the network to be trained across multiple scenes to learn a scene prior, enabling it to perform novel view synthesis in a feed-forward manner from a sparse set of views (as few as one).

3D Reconstruction Generalizable Novel View Synthesis +2

Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild

2 code implementations ECCV 2020 Jason Y. Zhang, Sam Pepose, Hanbyul Joo, Deva Ramanan, Jitendra Malik, Angjoo Kanazawa

We present a method that infers spatial arrangements and shapes of humans and objects in a globally consistent 3D scene, all from a single image in-the-wild captured in an uncontrolled environment.

3D Human Pose Estimation 3D Human Reconstruction +5

Shape and Viewpoint without Keypoints

no code implementations ECCV 2020 Shubham Goel, Angjoo Kanazawa, Jitendra Malik

We present a learning framework that learns to recover the 3D shape, pose and texture from a single image, trained on an image collection without any ground truth 3D shape, multi-view, camera viewpoints or keypoint supervision.

An Analysis of SVD for Deep Rotation Estimation

2 code implementations NeurIPS 2020 Jake Levinson, Carlos Esteves, Kefan Chen, Noah Snavely, Angjoo Kanazawa, Afshin Rostamizadeh, Ameesh Makadia

Symmetric orthogonalization via SVD, and closely related procedures, are well-known techniques for projecting matrices onto $O(n)$ or $SO(n)$.

3D Pose Estimation 3D Rotation Estimation

Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture from Images "In the Wild"

1 code implementation ICCV 2019 Silvia Zuffi, Angjoo Kanazawa, Tanya Berger-Wolf, Michael J. Black

In contrast to research on human pose, shape and texture estimation, training data for endangered species is limited, the animals are in complex natural scenes with occlusion, they are naturally camouflaged, travel in herds, and look similar to each other.

Pose Estimation Texture Synthesis

Predicting 3D Human Dynamics from Video

1 code implementation ICCV 2019 Jason Y. Zhang, Panna Felsen, Angjoo Kanazawa, Jitendra Malik

In this work, we present perhaps the first approach for predicting a future 3D mesh model sequence of a person from past video input.

3D Human Dynamics 3D Human Pose Estimation +3

PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization

1 code implementation ICCV 2019 Shunsuke Saito, Zeng Huang, Ryota Natsume, Shigeo Morishima, Angjoo Kanazawa, Hao Li

We introduce Pixel-aligned Implicit Function (PIFu), a highly effective implicit representation that locally aligns pixels of 2D images with the global context of their corresponding 3D object.

3D Human Pose Estimation 3D Human Reconstruction +4

Learning 3D Human Dynamics from Video

1 code implementation CVPR 2019 Angjoo Kanazawa, Jason Y. Zhang, Panna Felsen, Jitendra Malik

We present a framework that can similarly learn a representation of 3D dynamics of humans from video via a simple but effective temporal encoding of image features.

Ranked #17 on 3D Human Pose Estimation on 3DPW (Acceleration Error metric)

3D Human Dynamics 3D Human Pose Estimation

SFV: Reinforcement Learning of Physical Skills from Videos

1 code implementation8 Oct 2018 Xue Bin Peng, Angjoo Kanazawa, Jitendra Malik, Pieter Abbeel, Sergey Levine

In this paper, we propose a method that enables physically simulated characters to learn skills from videos (SFV).

Deep Reinforcement Learning Pose Estimation +2

Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow

5 code implementations ICLR 2019 Xue Bin Peng, Angjoo Kanazawa, Sam Toyer, Pieter Abbeel, Sergey Levine

By enforcing a constraint on the mutual information between the observations and the discriminator's internal representation, we can effectively modulate the discriminator's accuracy and maintain useful and informative gradients.

continuous-control Continuous Control +3

Lions and Tigers and Bears: Capturing Non-Rigid, 3D, Articulated Shape From Images

no code implementations CVPR 2018 Silvia Zuffi, Angjoo Kanazawa, Michael J. Black

Animals are widespread in nature and the analysis of their shape and motion is important in many fields and industries.

Learning Category-Specific Mesh Reconstruction from Image Collections

no code implementations ECCV 2018 Angjoo Kanazawa, Shubham Tulsiani, Alexei A. Efros, Jitendra Malik

The shape is represented as a deformable 3D mesh model of an object category where a shape is parameterized by a learned mean shape and per-instance predicted deformation.

Prediction

End-to-end Recovery of Human Shape and Pose

10 code implementations CVPR 2018 Angjoo Kanazawa, Michael J. Black, David W. Jacobs, Jitendra Malik

The main objective is to minimize the reprojection loss of keypoints, which allow our model to be trained using images in-the-wild that only have ground truth 2D annotations.

3D Hand Pose Estimation 3D Human Shape Estimation +5

Towards Accurate Markerless Human Shape and Pose Estimation over Time

no code implementations24 Jul 2017 Yinghao Huang, Federica Bogo, Christoph Lassner, Angjoo Kanazawa, Peter V. Gehler, Ijaz Akhter, Michael J. Black

Existing marker-less motion capture methods often assume known backgrounds, static cameras, and sequence specific motion priors, which narrows its application scenarios.

Pose Estimation

3D Menagerie: Modeling the 3D shape and pose of animals

no code implementations CVPR 2017 Silvia Zuffi, Angjoo Kanazawa, David Jacobs, Michael J. Black

The best human body models are learned from thousands of 3D scans of people in specific poses, which is infeasible with live animals.

WarpNet: Weakly Supervised Matching for Single-view Reconstruction

no code implementations CVPR 2016 Angjoo Kanazawa, David W. Jacobs, Manmohan Chandraker

This is in contrast to prior works that require part annotations, since matching objects across class and pose variations is challenging with appearance features alone.

Learning 3D Deformation of Animals from 2D Images

no code implementations28 Jul 2015 Angjoo Kanazawa, Shahar Kovalsky, Ronen Basri, David W. Jacobs

In this paper, we show that such information can be learned from user-clicked 2D images and a template 3D model of the target animal.

Locally Scale-Invariant Convolutional Neural Networks

no code implementations16 Dec 2014 Angjoo Kanazawa, Abhishek Sharma, David Jacobs

We show on a modified MNIST dataset that when faced with scale variation, building in scale-invariance allows ConvNets to learn more discriminative features with reduced chances of over-fitting.

Cannot find the paper you are looking for? You can Submit a new open access paper.