← Search

Saining Zhang

7 accepted papers

2026

Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimation

ICRA 2026poster

Transparent objects remain notoriously hard for perception systems: refraction, reflection and transmission break the assumptions behind stereo, ToF and purely discriminative monocular depth, causing holes and temporally unstable estimates. Our key observation is that modern video diffusion models a…

2026

Light-X: Generative 4D Video Rendering with Camera and Illumination Control

ICLR 2026poster

Recent advances in illumination control extend image-based methods to video, yet still facing a trade-off between lighting fidelity and temporal consistency. Moving beyond relighting, a key step toward generative modeling of real-world scenes is the joint control of camera trajectory and illuminatio…

Cited by 12SourcecodeScholar
2026

WEAVE: Unleashing and Benchmarking the In-context Interleaved Comprehension and Generation

CVPR 2026

Recent unified multimodal models (UMMs) have achieved remarkable progress in visual comprehension and generation. However, existing datasets and benchmarks focus predominantly on single-turn interactions, overlooking the multi-turn, context-dependent nature of real-world image creation and editing.

Cited by 0SourceScholar
2025

CRUISE: Cooperative Reconstruction and Editing in V2X Scenarios using Gaussian Splatting

IROS 2025

Vehicle-to-everything (V2X) communication plays a crucial role in autonomous driving, enabling cooperation between vehicles and infrastructure. While simulation has significantly contributed to various autonomous driving tasks, its potential for data generation and augmentation in V2X scenarios rema

Cited by 4SourcecodeScholar
2025

GS-Occ3D: Scaling Vision-only Occupancy Reconstruction with Gaussian Splatting

ICCV 2025poster

Occupancy is crucial for autonomous driving, providing essential geometric priors for perception and planning. However, existing methods predominantly rely on LiDAR-based occupancy annotations, which limits scalability and prevents leveraging vast amounts of potential crowdsourced data for auto-labe…

2025

Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting

NeurIPS 2025poster

Neural rendering techniques, including NeRF and Gaussian Splatting (GS), rely on photometric consistency to produce high-quality reconstructions. However, in real-world driving scenarios, it is challenging to guarantee perfect photometric consistency in acquired images. Appearance codes have been wi…

Cited by 0SourcecodeScholar