activity
20232026
collaborators

6 papers

cs.CV2026

Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation

Shuhong Zheng, Aashish Kumar Misraa, Yu-Teng Li +2

Subject-driven image generation aims to synthesize new images that preserve the identity of the given subject while following textual instructions. Existing approaches often encode…

cs.CV2026

Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers

Shuhong Zheng, Michael Oechsle, Erik Sandström +3

Visual geometry transformers have become powerful architectures for multi-view 3D reconstruction, enabling joint prediction of multiple 3D attributes in a feed-forward manner. Howe…

cs.CV2025

Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling

Shuhong Zheng, Ashkan Mirzaei, Igor Gilitschenski

Current 3D/4D generation methods are usually optimized for photorealism, efficiency, and aesthetics. However, they often fail to preserve the semantic identity of the subject acros…

cs.CV2024

Diff-2-in-1: Bridging Generation and Dense Perception with Diffusion Models

Shuhong Zheng, Zhipeng Bao, Ruoyu Zhao +2

Beyond high-fidelity image synthesis, diffusion models have recently exhibited promising results in dense visual perception tasks. However, most existing work treats diffusion mode…

cs.CV2024

Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding

Yunze Man, Shuhong Zheng, Zhipeng Bao +3

Complex 3D scene understanding has gained increasing attention, with scene encoding strategies playing a crucial role in this success. However, the optimal scene encoding strategie…

cs.CV2023

Multi-task View Synthesis with Neural Radiance Fields

Shuhong Zheng, Zhipeng Bao, Martial Hebert +1

Multi-task visual learning is a critical aspect of computer vision. Current research, however, predominantly concentrates on the multi-task dense prediction setting, which overlook…