2 citations · 3 across the 12 of their papers we have counts for
15 papers
Disentangling Task-Relevant Latent Dynamics for Reward Modeling
Dayou Li, Jionghao Wang, Peihao Wang +9
Reward design remains a major bottleneck for reinforcement learning in robotic manipulation. Handcrafted dense rewards can compensate for the limited guidance provided by sparse re…
S4VY: Segment Anything in Feed-Forward 4D Visual Geometry
Jingdong Zhang, Xin Li, Jan Kautz +2
Accurate instance segmentation in dynamic scenes is important for downstream applications such as robotics and autonomous driving. Existing Segment Anything models operate primaril…
NBS: No Bias Stereo
Vage Taamazyan, Zhuowen Shen, Stefan Hinterstoisser +6
Stereo reconstruction is one of the last remaining Computer Vision tasks where all state-of-the-art methods employ a heavy architectural inductive bias. Even though it has been dem…
Learning What Matters: Adaptive Information-Theoretic Objectives for Robot Exploration
Youwei Yu, Jionghao Wang, Zhengming Yu +2
Designing learnable information-theoretic objectives for robot exploration remains challenging. Such objectives aim to guide exploration toward data that reduces uncertainty in mod…
Beyond Thinking: Imagining in 360 for Humanoid Visual Search
Jingdong Zhang, Yizhou Wang, Zhengzhong Tu +3
Humanoid Visual Search (HVS) requires agents to actively explore immersive 360 environments. While prior methods treat this as a monolithic task relying on cumulative, mult…
DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models
Zhengming Yu, Li Ma, Mingming He +11
Most digital videos are stored in 8-bit low dynamic range (LDR) formats, where much of the original high dynamic range (HDR) scene radiance is lost due to saturation and quantizati…
RecGen3D: Reconstruction-Guided 3D Generation in a Shared Canonical Space
Zhisheng Huang, Jiahao Chen, Cheng Lin +10
Sparse-view 3D modeling represents a fundamental tension between reconstruction fidelity and generative plausibility. While feed-forward reconstruction excels in efficiency and inp…
3DGS-HPC: Distractor-free 3D Gaussian Splatting with Hybrid Patch-wise Classification
Jiahao Chen, Yipeng Qin, Ganlong Zhao +3
3D Gaussian Splatting (3DGS) has demonstrated remarkable performance in novel view synthesis and 3D scene reconstruction, but its quality often degrades in real-world environments…
MTPano: Multi-Task Panoramic Scene Understanding via Label-Free Integration of Dense Prediction Priors
Jingdong Zhang, Xiaohang Zhan, Lingzhi Zhang +5
Comprehensive panoramic scene understanding is critical for immersive applications, yet it remains challenging due to the scarcity of high-resolution, multi-task annotations. While…
UniSER: A Foundation Model for Unified Soft Effects Removal
Jingdong Zhang, Lingzhi Zhang, Qing Liu +12
Digital images are often degraded by soft effects such as lens flare, haze, shadows, and reflections, which reduce aesthetics even though the underlying pixels remain partially vis…
SPGen: Spherical Projection as Consistent and Flexible Representation for Single Image 3D Shape Generation
Jingdong Zhang, Weikai Chen, Yuan Liu +6
Existing single-view 3D generative models typically adopt multiview diffusion priors to reconstruct object surfaces, yet they remain prone to inter-view inconsistencies and are una…
Controllable 3D Outdoor Scene Generation via Scene Graphs
Yuheng Liu, Xinke Li, Yuning Zhang +6
Three-dimensional scene generation is crucial in computer vision, with applications spanning autonomous driving, gaming and the metaverse. Current methods either lack user control…
SolidGS: Consolidating Gaussian Surfel Splatting for Sparse-View Surface Reconstruction
Zhuowen Shen, Yuan Liu, Zhang Chen +9
Gaussian splatting has achieved impressive improvements for both novel-view synthesis and surface reconstruction from multi-view images. However, current methods still struggle to…
AURORA: Automated Unleash of 3D Room Outlines for VR Applications
Huijun Han, Yongqing Liang, Yuanlong Zhou +3
Creating realistic VR experiences is challenging due to the labor-intensive process of accurately replicating real-world details into virtual scenes, highlighting the need for auto…
Multi-Task Label Discovery via Hierarchical Task Tokens for Partially Annotated Dense Predictions
Jingdong Zhang, Hanrong Ye, Xin Li +2
In recent years, simultaneous learning of multiple dense prediction tasks with partially annotated label data has emerged as an important research area. Previous works primarily fo…