Search Results for author:
Found 50 papers, 26 papers with code
Colorization of Depth Map via Disentanglement
Vision perception is one of the most important components for a computer or robot to understand the surrounding scene and achieve autonomous applications.
A Recipe for CAC: Mosaic-based Generalized Loss for Improved Class-Agnostic Counting
Class agnostic counting (CAC) is a vision task that can be used to count the total occurrence number of any given reference objects in the query image.
MCPNet: An Interpretable Classifier via Multi-Level Concept Prototypes
Addressing this gap, we introduce the Multi-Level Concept Prototypes Classifier (MCPNet), an inherently interpretable model.
MENTOR: Multilingual tExt detectioN TOward leaRning by analogy
Text detection is frequently used in vision-based mobile robots when they need to interpret texts in their surroundings to perform a given task.
Improving Robustness for Joint Optimization of Camera Poses and Decomposed Low-Rank Tensorial Radiance Fields
In this paper, we propose an algorithm that allows joint refinement of camera pose and scene geometry represented by decomposed low-rank tensor, using only 2D images as supervision.
AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors
We formulate deepfake detection as a visual question answering problem, and tune soft prompts for InstructBLIP to distinguish a query image is real or fake.
Skin the sheep not only once: Reusing Various Depth Datasets to Drive the Learning of Optical Flow
Lastly, as the optical flow maps under different geometric augmentations actually exhibit distinct characteristics, an auxiliary classifier which trains to identify the type of augmentation from the appearance of the flow map is utilized to further enhance the learning of the optical flow estimator.
Masking Improves Contrastive Self-Supervised Learning for ConvNets, and Saliency Tells You Where
While image data starts to enjoy the simple-but-effective self-supervised learning scheme built upon masking and self-reconstruction objective thanks to the introduction of tokenization procedure and vision transformer backbone, convolutional neural networks as another important and widely-adopted architecture for image data, though having contrastive-learning techniques to drive the self-supervised learning, still face the difficulty of leveraging such straightforward and general masking operation to benefit their learning process significantly.
Transformer-based Image Compression with Variable Image Quality Objectives
This paper presents a Transformer-based image compression system that allows for a variable image quality objective according to the user's preference.
Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts
In this work, we propose Prompting4Debugging (P4D) as a debugging and red-teaming tool that automatically finds problematic prompts for diffusion models to test the reliability of a deployed safety mechanism.
TransTIC: Transferring Transformer-based Image Compression from Human Perception to Machine Perception
This work aims for transferring a Transformer-based image compression codec from human perception to machine perception without fine-tuning the codec.
Transformer-based Variable-rate Image Compression with Region-of-interest Control
Our prompt generation networks generate content-adaptive tokens according to the input image, an ROI mask, and a rate parameter.
Multimodal Prompting with Missing Modalities for Visual Recognition
In this paper, we tackle two challenges in multimodal learning for visual recognition: 1) when missing-modality occurs either during training or testing in real-world situations; and 2) when the computation resources are not available to finetune on heavy transformer models.
Mitigating Forgetting in Online Continual Learning via Contrasting Semantically Distinct Augmentations
Online continual learning (OCL) aims to enable model learning from a non-stationary data stream to continuously acquire new knowledge as well as retain the learnt one, under the constraints of having limited system size and computational cost, in which the main challenge comes from the "catastrophic forgetting" issue -- the inability to well remember the learnt knowledge while learning the new ones.
3D-PL: Domain Adaptive Depth Estimation with 3D-aware Pseudo-Labeling
In this paper, we develop a domain adaptation framework via generating reliable pseudo ground truths of depth from real data to provide direct supervisions.
BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation
Thus, state-of-the-art frameworks for monocular 360 depth estimation such as bi-projection fusion in BiFuse are proposed.
Ranked #12 on
Depth Estimation
on Stanford2D3D Panoramic
Adaptively-Realistic Image Generation from Stroke and Sketch with Diffusion Model
Generating images from hand-drawings is a crucial and fundamental task in content creation.
Vector Quantized Image-to-Image Translation
For example, it provides style variability for image generation and extension, and equips image-to-image translation with further extension capabilities.
Self-Supervised Feature Learning from Partial Point Clouds via Pose Disentanglement
Self-supervised learning on point clouds has gained a lot of attention recently, since it addresses the label-efficiency and domain-gap problems on point cloud tasks.
Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis
Basically, given only a small set of detectors that are learned to recognize some manually annotated attributes (i. e., the seen attributes), we aim to synthesize the detectors of novel attributes in a zero-shot learning manner.
An Unsupervised Video Game Playstyle Metric via State Discretization
In this paper, we propose the first metric for video game playstyles directly from the game observations and actions, without any prior specification on the playstyle in the target game.
Towards Interpretable Deep Networks for Monocular Depth Estimation
Based on our observations, we quantify the interpretability of a deep MDE network by the depth selectivity of its hidden units.
Learning Facial Representations from the Cycle-consistency of Face
The main idea of the facial motion cycle-consistency is that, given a face with expression, we can perform de-expression to a neutral face via the removal of facial motion and further perform re-expression to reconstruct back to the original face.
MAML is a Noisy Contrastive Learner in Classification
Model-agnostic meta-learning (MAML) is one of the most popular and widely adopted meta-learning algorithms, achieving remarkable success in various learning problems.
LED2-Net: Monocular 360deg Layout Estimation via Differentiable Depth Rendering
Although significant progress has been made in room layout estimation, most methods aim to reduce the loss in the 2D pixel coordinate rather than exploiting the room structure in the 3D space.
RPG: Learning Recursive Point Cloud Generation
In this paper we propose a novel point cloud generator that is able to reconstruct and generate 3D point clouds composed of semantic parts.
Stylizing 3D Scene via Implicit Representation and HyperNetwork
Our framework consists of two components: an implicit representation of the 3D scene with the neural radiance fields model, and a hypernetwork to transfer the style information into the scene representation.
Robust 360-8PA: Redesigning The Normalized 8-point Algorithm for 360-FoV Images
This paper presents a novel preconditioning strategy for the classic 8-point algorithm (8-PA) for estimating an essential matrix from 360-FoV images (i. e., equirectangular images) in spherical projection.
LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth Rendering
Although significant progress has been made in room layout estimation, most methods aim to reduce the loss in the 2D pixel coordinate rather than exploiting the room structure in the 3D space.
3D Room Layouts From A Single RGB Panorama
Depth Estimation
+2
Bridging the Visual Gap: Wide-Range Image Blending
In this paper we propose a new problem scenario in image processing, wide-range image blending, which aims to smoothly merge two different input photos into a panorama by generating novel image content for the intermediate region between them.
Domain Adaptation for Learning Generator from Paired Few-Shot Data
We propose a Paired Few-shot GAN (PFS-GAN) model for learning generators with sufficient source data and a few target data.
Dual-Stream Fusion Network for Spatiotemporal Video Super-Resolution
Our method is based on an important observation that: even the direct cascade of prior research in spatial and temporal super-resolution can achieve the spatiotemporal upsampling, changing orders for combining them would lead to results with a complementary property.
Spectral Analysis for Semantic Segmentation with Applications on Feature Truncation and Weak Annotation
We propose a spectral analysis to investigate the correlations among the resolution of the down sampled grid, the loss function and the accuracy of the SSNNs.
Class-incremental Learning with Rectified Feature-Graph Preservation
In this paper, we address the problem of distillation-based class-incremental learning with a single head.
Benefiting Deep Latent Variable Models via Learning the Prior and Removing Latent Regularization
There exist many forms of deep latent variable models, such as the variational autoencoder and adversarial autoencoder.
Variational Autoencoders with Normalizing Flow Decoders
Recently proposed normalizing flow models such as Glow have been shown to be able to generate high quality, high dimensional images with relatively fast sampling speed.
LayoutMP3D: Layout Annotation of Matterport3D
Inferring the information of 3D layout from a single equirectangular panorama is crucial for numerous applications of virtual reality or robotics (e. g., scene understanding and navigation).
360SD-Net: 360° Stereo Depth Estimation with Learnable Cost Volume
Recently, end-to-end trainable deep neural networks have significantly improved stereo depth estimation for perspective images.
Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence
In this paper, we propose a single and principled network to jointly learn spatiotemporal correspondence for stereo matching and flow estimation, with a newly designed geometric connection as the unsupervised signal for temporally adjacent stereo pairs.
3D LiDAR and Stereo Fusion using Stereo Matching Network with Conditional Cost Volume Normalization
The complementary characteristics of active and passive depth sensing techniques motivate the fusion of the Li-DAR sensor and stereo camera for improved depth perception.
All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentation
In this paper we tackle the problem of unsupervised domain adaptation for the task of semantic segmentation, where we attempt to transfer the knowledge learned upon synthetic datasets with ground-truth labels to real-world images without any annotation.
Ranked #25 on
Image-to-Image Translation
on SYNTHIA-to-Cityscapes
Plug-and-Play: Improve Depth Estimation via Sparse Data Propagation
We propose a novel plug-and-play (PnP) module for improving depth prediction with taking arbitrary patterns of sparse depths as input.
Self-Contained Stylization via Steganography for Reverse and Serial Style Transfer
Style transfer has been widely applied to give real-world images a new artistic look.
Summarizing First-Person Videos from Third Persons' Points of View
Video highlight or summarization is among interesting topics in computer vision, which benefits a variety of applications like viewing, searching, or storage.
Summarizing First-Person Videos from Third Persons' Points of Views
Video highlight or summarization is among interesting topics in computer vision, which benefits a variety of applications like viewing, searching, or storage.
Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation
While representation learning aims to derive interpretable features for describing visual data, representation disentanglement further results in such features so that particular image attributes can be identified and manipulated.
Towards Segmenting Consumer Stereo Videos: Benchmark, Baselines and Ensembles
Are we ready to segment consumer stereo videos?
STD2P: RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling
The proposed network produces a high quality segmentation of a single image by leveraging information from additional views of the same scene.
Ranked #96 on
Semantic Segmentation
on NYU Depth v2
See the Difference: Direct Pre-Image Reconstruction and Pose Estimation by Differentiating HOG
The Histogram of Oriented Gradient (HOG) descriptor has led to many advances in computer vision over the last decade and is still part of many state of the art approaches.
Multi-class Video Co-segmentation with a Generative Multi-video Model
This is a clear mismatch to the challenges that we are facing with videos from online resources or consumer videos.
