64 citations · 210 across the 14 of their papers we have counts for
14 papers
Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance
Shenhao Zhu, Junming Leo Chen, Zuozhuo Dai +6
In this study, we introduce a methodology for human image animation by leveraging a 3D human parametric model within a latent diffusion framework to enhance shape alignment and mot…
EffiVED:Efficient Video Editing via Text-instruction Diffusion Models
Zhenghao Zhang, Zuozhuo Dai, Long Qin +1
Large-scale text-to-video models have shown remarkable abilities, but their direct application in video editing remains challenging due to limited available datasets. Current video…
Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particle
Youtian Lin, Zuozhuo Dai, Siyu Zhu +1
We introduce Gaussian-Flow, a novel point-based approach for fast dynamic scene reconstruction and real-time rendering from both multi-view and monocular videos. In contrast to the…
AnimateAnything: Fine-Grained Open Domain Image Animation with Motion Guidance
Zuozhuo Dai, Zhenghao Zhang, Yao Yao +4
Image animation is a key task in computer vision which aims to generate dynamic visual content from static image. Recent image animation methods employ neural based rendering techn…
Fine-grained Text-Video Retrieval with Frozen Image Encoders
Zuozhuo Dai, Fangtao Shao, Qingkun Su +2
State-of-the-art text-video retrieval (TVR) methods typically utilize CLIP and cosine similarity for efficient retrieval. Meanwhile, cross attention methods, which employ a transfo…
UVOSAM: A Mask-free Paradigm for Unsupervised Video Object Segmentation via Segment Anything Model
Zhenghao Zhang, Shengfan Zhang, Zhichao Wei +2
The current state-of-the-art methods for unsupervised video object segmentation (UVOS) require extensive training on video datasets with mask annotations, limiting their effectiven…
Towards Robust Video Instance Segmentation with Temporal-Aware Transformer
Zhenghao Zhang, Fangtao Shao, Zuozhuo Dai +1
Most existing transformer based video instance segmentation methods extract per frame features independently, hence it is challenging to solve the appearance deformation problem. I…
RCP: Recurrent Closest Point for Scene Flow Estimation on 3D Point Clouds
Xiaodong Gu, Chengzhou Tang, Weihao Yuan +3
3D motion estimation including scene flow and point cloud registration has drawn increasing interest. Inspired by 2D flow estimation, recent methods employ deep neural networks to…
NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation
Weihao Yuan, Xiaodong Gu, Zuozhuo Dai +2
Estimating the accurate depth from a single image is challenging since it is inherently ambiguous and ill-posed. While recent works design increasingly complicated and powerful net…
DRO: Deep Recurrent Optimizer for Video to Depth
Xiaodong Gu, Weihao Yuan, Zuozhuo Dai +4
There are increasing interests of studying the video-to-depth (V2D) problem with machine learning techniques. While earlier methods directly learn a mapping from images to depth ma…
Cluster Contrast for Unsupervised Person Re-Identification
Zuozhuo Dai, Guangyuan Wang, Weihao Yuan +3
State-of-the-art unsupervised re-ID methods train the neural networks using a memory-based non-parametric softmax loss. Instance feature vectors stored in memory are assigned pseud…
MeshMVS: Multi-View Stereo Guided Mesh Reconstruction
Rakesh Shrestha, Zhiwen Fan, Qingkun Su +3
Deep learning based 3D shape generation methods generally utilize latent features extracted from color images to encode the semantics of objects and guide the shape generation proc…
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching
Xiaodong Gu, Zhiwen Fan, Zuozhuo Dai +3
The deep multi-view stereo (MVS) and stereo matching approaches generally construct 3D cost volumes to regularize and regress the output depth or disparity. These methods are limit…
Batch DropBlock Network for Person Re-identification and Beyond
Zuozhuo Dai, Mingqiang Chen, Xiaodong Gu +2
Since the person re-identification task often suffers from the problem of pose changes and occlusions, some attentive local features are often suppressed when training CNNs. In thi…