Search Results for author:
Found 53 papers, 15 papers with code
OracleFusion: Assisting the Decipherment of Oracle Bone Script with Structurally Constrained Semantic Typography
As one of the earliest ancient languages, Oracle Bone Script (OBS) encapsulates the cultural records and intellectual expressions of ancient civilizations.
4Real-Video-V2: Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation
We propose the first framework capable of computing a 4D spatio-temporal grid of video frames and 3D Gaussian particles for each time step using a feed-forward architecture.
Grounding Chest X-Ray Visual Question Answering with Generated Radiology Reports
Taking inspiration from 'Chain-of-Thought reasoning', we demonstrate that performance on the CXR VQA task can be improved by grounding the answer generator module with a radiology report predicted for the same CXR.
Conditional Panoramic Image Generation via Masked Autoregressive Modeling
Recent progress in panoramic image generation has underscored two critical limitations in existing approaches.
TMCIR: Token Merge Benefits Composed Image Retrieval
This mechanism dynamically balances visual and textual representations within the contrastive learning pipeline, optimizing the composed feature for retrieval.
Ranked #1 on
Image Retrieval
on CIRR
Towards Affordance-Aware Articulation Synthesis for Rigged Objects
However, articulating the rigs into realistic affordance-aware postures (e. g., following the context, respecting the physics and the personalities of the object) remains time-consuming and heavily relies on human labor from experienced artists.
PrEditor3D: Fast and Precise 3D Shape Editing
The edited 3D mesh aligns well with the prompts, and remains identical for regions that are not intended to be altered.
4Real-Video: Learning Generalizable Photo-Realistic 4D Video Diffusion
We propose a novel two-stream architecture.
DELTA: Dense Efficient Long-range 3D Tracking for any video
Our method provides a robust solution for applications requiring fine-grained, long-term motion tracking in 3D space.
Pixel-Aligned Multi-View Generation with Depth Guided Decoder
During inference, we employ a rapid multi-view to 3D reconstruction approach, NeuS, to obtain coarse depth for the depth-truncated epipolar attention.
VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control
Recently, new methods demonstrate the ability to generate videos with controllable camera poses these techniques leverage pre-trained U-Net-based diffusion models that explicitly disentangle spatial and temporal generation.
Oracle Bone Inscriptions Multi-modal Dataset
Oracle bone inscriptions(OBI) is the earliest developed writing system in China, bearing invaluable written exemplifications of early Shang history and paleography.
Lightweight Predictive 3D Gaussian Splats
Our key observation is that nearby points in the scene can share similar representations.
4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models
We then learn the canonical 3D representation of the video using a freeze-time video, delicately generated from the reference video.
GTR: Improving Large 3D Reconstruction Models through Geometry and Texture Refinement
Our method takes inspiration from large reconstruction models like LRM that use a transformer-based triplane generator and a Neural Radiance Field (NeRF) model trained on multi-view images.
SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow
For image synthesis, we propose a finite perturbation approach to enhance the diversity of generated results without changing the semantic categories.
3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting
This results in a lack of a unified approach to effectively control and manipulate scenes at the 3D level with different levels of granularity.
Leader Reward for POMO-Based Neural Combinatorial Optimization
We demonstrate that Leader Reward greatly improves the quality of the optimal solutions generated by the model.
Explore In-Context Segmentation via Latent Diffusion Models
In-context segmentation has drawn more attention with the introduction of vision foundation models.
AToM: Amortized Text-to-Mesh using 2D Diffusion
We introduce Amortized Text-to-Mesh (AToM), a feed-forward text-to-mesh framework optimized across multiple text prompts simultaneously.
Diffusion Priors for Dynamic View Synthesis from Monocular Videos
Dynamic novel view synthesis aims to capture the temporal evolution of visual content within videos.
DualVAE: Dual Disentangled Variational AutoEncoder for Recommendation
To address this problem, we propose a Dual Disentangled Variational AutoEncoder (DualVAE) for collaborative recommendation, which combines disentangled representation learning with variational inference to facilitate the generation of implicit interaction data.
Towards Text-guided 3D Scene Composition
We marry the locality of objects with globality of scenes by introducing a hybrid 3D representation - explicit for objects and implicit for scenes.
LGMRec: Local and Global Graph Learning for Multimodal Recommendation
The multimodal recommendation has gradually become the infrastructure of online media platforms, enabling them to provide personalized service to users through a joint modeling of user historical behaviors (e. g., purchases, clicks) and item various modalities (e. g., visual and textual).
Virtual Pets: Animatable Animal Generation in 3D Scenes
Toward unlocking the potential of generative models in immersive 4D experiences, we introduce Virtual Pet, a novel pipeline to model realistic and diverse motions for target animal species within a 3D environment.
SceneWiz3D: Towards Text-guided 3D Scene Composition
We are witnessing significant breakthroughs in the technology for generating 3D objects from text.
Controllable Chest X-Ray Report Generation from Longitudinal Representations
Previous approaches to automated radiology reporting generally do not provide the prior study as input, precluding comparison which is required for clinical accuracy in some types of scans, and offer only unreliable methods of interpretability.
Finding-Aware Anatomical Tokens for Chest X-Ray Automated Reporting
Automated approaches to radiology reporting require the image to be encoded into a suitable token representation for input to the language model.
AutoDecoding Latent 3D Diffusion Models
We present a novel approach to the generation of static and articulated 3D assets that has a 3D autodecoder at its core.
Reconstructing Animatable Categories from Videos
Building animatable 3D models is challenging due to the need for 3D scans, laborious registration, and manual rigging, which are difficult to scale to arbitrary categories.
3D Shape Reconstruction from Videos
Dynamic Reconstruction
+1
Flow supervision for Deformable NeRF
In this paper we present a new method for deformable NeRF that can directly use optical flow as supervision.
The role of noise in denoising models for anomaly detection in medical images
Denoising methods, for instance classical denoising autoencoders (DAEs) and more recently emerging diffusion models, are a promising approach, however naive application of pixelwise noise leads to poor anomaly detection performance.
MDGCF: Multi-Dependency Graph Collaborative Filtering with Neighborhood- and Homogeneous-level Dependencies
Specifically, for neighborhood-level dependencies, we explicitly consider both popularity score and preference correlation by designing a joint neighborhood-level dependency weight, based on which we construct a neighborhood-level dependencies graph to capture higher-order interaction features.
MBW: Multi-view Bootstrapping in the Wild
Our Multi-view Bootstrapping in the Wild (MBW) approach demonstrates impressive results on standard human datasets, as well as tigers, cheetahs, fish, colobus monkeys, chimpanzees, and flamingos from videos captured casually in a zoo.
3D Reconstruction
Semi-supervised 2D and 3D landmark labeling
+1
Neural Prior for Trajectory Estimation
Here, we propose a neural trajectory prior to capture continuous spatio-temporal information without the need for offline data.
High Fidelity 3D Reconstructions with Limited Physical Views
Multi-view triangulation is the gold standard for 3D reconstruction from 2D correspondences given known calibration and sufficient views.
Neural Trajectory Fields for Dynamic Novel View Synthesis
Recent approaches to render photorealistic views from a limited set of photographs have pushed the boundaries of our interactions with pictures of static scenes.
PAUL: Procrustean Autoencoder for Unsupervised Lifting
Recent success in casting Non-rigid Structure from Motion (NRSfM) as an unsupervised deep learning problem has raised fundamental questions about what novelty in NRSfM prior could the deep learning offer.
SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images
Dense 3D object reconstruction from a single image has recently witnessed remarkable advances, but supervising neural networks with ground-truth 3D shapes is impractical due to the laborious process of creating paired image-shape datasets.
3D Object Reconstruction From A Single Image
3D Reconstruction
A Light Heterogeneous Graph Collaborative Filtering Model using Textual Information
Afterward, by performing a simplified RGCN-based node information propagation on the constructed heterogeneous graph, the embeddings of users and items can be adjusted with textual knowledge, which effectively alleviates the negative effects of data sparsity.
A Text-based Deep Reinforcement Learning Framework for Interactive Recommendation
IRSs usually face the large discrete action space problem, which makes most of the existing RL-based recommendation methods inefficient.
Deep NRSfM++: Towards Unsupervised 2D-3D Lifting in the Wild
The recovery of 3D shape and pose from 2D landmarks stemming from a large ensemble of images can be viewed as a non-rigid structure from motion (NRSfM) problem.
Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning
This alleviates the data bottleneck, which is one of the major concern for supervised methods.
Ranked #21 on
Weakly-supervised 3D Human Pose Estimation
on Human3.6M
Web Stereo Video Supervision for Depth Prediction from Dynamic Scenes
We present a fully data-driven method to compute depth from diverse monocular video sequences that contain large amounts of non-rigid objects, e. g., people.
Deep Convolutional Compressed Sensing for LiDAR Depth Completion
In this paper we consider the problem of estimating a dense depth map from a set of sparse LiDAR points.
Learning Depth from Monocular Videos using Direct Methods
The ability to predict depth from a single image - using recent advances in CNNs - is of increasing interest to the vision community.
Semantic Photometric Bundle Adjustment on Natural Sequences
More recently, excellent results have been attained through the application of photometric bundle adjustment (PBA) methods -- which directly minimize the photometric error across frames.
Object-Centric Photometric Bundle Adjustment with Deep Shape Prior
Reconstructing 3D shapes from a sequence of images has long been a problem of interest in computer vision.
Rethinking Reprojection: Closing the Loop for Pose-Aware Shape Reconstruction From a Single Image
An emerging problem in computer vision is the reconstruction of 3D shape and pose of an object from a single image.
Rethinking Reprojection: Closing the Loop for Pose-aware ShapeReconstruction from a Single Image
An emerging problem in computer vision is the reconstruction of 3D shape and pose of an object from a single image.
Deep-LK for Efficient Adaptive Object Tracking
In this paper we present a new approach for efficient regression based object tracking which we refer to as Deep- LK.
Object Proposal by Multi-Branch Hierarchical Segmentation
Hierarchical segmentation based object proposal methods have become an important step in modern object detection paradigm.
An non-uniform sampling strategy for physiological signals component analysis
The conventional approach cannot meet the requirement of physiological signal analysis to extract the main component of the acquired signal.
