30 citations · 64 across the 23 of their papers we have counts for
27 papers
Gate3DGen: A Pre-processing Model that Selectively Purifies Real-World Images for 3D Generation
Xiaolin Li, Zihao Huang, Fanpeng Meng +5
Single-image 3D generation has achieved high fidelity on curated benchmarks, yet degrades sharply on real-world images with uneven illumination, blur, and occlusions. Purifying suc…
SUPRA-TEX: 3D Generation with Super-Aligned Texture
Chen Yang, Jiemin Fang, Fanpeng Meng +5
Single image 3D generation aims to dress a given 3D mesh with relightable materials while faithfully preserving the visual details of a reference image. Existing methods either int…
Reconstructing the Dynamic World: A Representation-Centric View of 4D Scene Reconstruction
Ziren Gong, Guo Chen, Yongjia Li +13
4D scene reconstruction aims to recover the evolving geometry, appearance, and motion of dynamic environments from visual observations. Despite substantial progress in neural scene…
SCULPT: Subtractive Composition for 3D Part Generation
Sikuang Li, Chen Yang, Jiemin Fang +5
Part-aware 3D generation aims to create digital assets that are coherent as complete objects while exposing structural parts for editing, material assignment, animation, and reuse.…
GrainGS: Gradient-Decoupled Gaussian Splatting for Efficient Dynamic Novel View Synthesis
Jiahao He, Yihua Shao, Zhengkai Zhao +6
Dynamic scene reconstruction with 3D Gaussian Splatting requires a balance between fine-grained motion modeling, structural stability, and compact representation. Existing per-prim…
ProxyUp: Training-Free Proxy-Conditioned Video Generation for Controllable Dynamics
Zanwei Zhou, Jiazhong Cen, Jiemin Fang +7
Precise control over complex dynamics remains challenging for modern video generative models, as text prompts alone often cannot specify physically plausible, fine-grained motion a…
Text-Image Conditioned 3D Generation
Jiazhong Cen, Jiemin Fang, Sikuang Li +8
High-quality 3D assets are essential for VR/AR, industrial design, and entertainment, motivating growing interest in generative models that create 3D content from user prompts. Mos…
AI Decodes Historical Chinese Archives to Reveal Lost Climate History
Sida He, Lingxi Xie, Xiaopeng Zhang +1
Historical archives contain qualitative descriptions of climate events, yet converting these into quantitative records has remained a fundamental challenge. Here we introduce a par…
WorldGrow: Generating Infinite 3D World
Sikuang Li, Chen Yang, Jiemin Fang +6
We tackle the challenge of generating the infinitely extendable 3D world -- large, continuous environments with coherent geometry and realistic appearance. Existing methods face ke…
UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generation
Guanjun Wu, Jiemin Fang, Chen Yang +11
High-fidelity 3D asset generation is crucial for various industries. While recent 3D pretrained models show strong capability in producing realistic content, most are built upon di…
Few-step Flow for 3D Generation via Marginal-Data Transport Distillation
Zanwei Zhou, Taoran Yi, Jiemin Fang +5
Flow-based 3D generation models typically require dozens of sampling steps during inference. Though few-step distillation methods, particularly Consistency Models (CMs), have achie…
Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds
Jia Lu, Taoran Yi, Jiemin Fang +6
Reconstructing 3D human bodies from sparse views has been an appealing topic, which is crucial to broader the related applications. In this paper, we propose a quite challenging bu…
Tackling View-Dependent Semantics in 3D Language Gaussian Splatting
Jiazhong Cen, Xudong Zhou, Jiemin Fang +5
Recent advancements in 3D Gaussian Splatting (3D-GS) enable high-quality 3D scene reconstruction from RGB images. Many studies extend this paradigm for language-driven open-vocabul…
Dereflection Any Image with Diffusion Priors and Diversified Data
Jichen Hu, Chen Yang, Zanwei Zhou +4
Reflection removal of a single image remains a highly challenging task due to the complex entanglement between target scenes and unwanted reflections. Despite significant progress,…
LiftImage3D: Lifting Any Single Image to 3D Gaussians with Video Generation Priors
Yabo Chen, Chen Yang, Jiemin Fang +6
Single-image 3D reconstruction remains a fundamental challenge in computer vision due to inherent geometric ambiguities and limited viewpoint information. Recent advances in Latent…
Segment Any 4D Gaussians
Shengxiang Ji, Guanjun Wu, Jiemin Fang +5
Modeling, understanding, and reconstructing the real world are crucial in XR/VR. Recently, 3D Gaussian Splatting (3D-GS) methods have shown remarkable success in modeling and under…
SAM-CP: Marrying SAM with Composable Prompts for Versatile Segmentation
Pengfei Chen, Lingxi Xie, Xinyue Huo +5
The Segment Anything model (SAM) has shown a generalized ability to group image pixels into patches, but applying it to semantic-aware segmentation still faces major challenges. Th…
GaussianDreamerPro: Text to Manipulable 3D Gaussians with Highly Enhanced Quality
Taoran Yi, Jiemin Fang, Zanwei Zhou +7
Recently, 3D Gaussian splatting (3D-GS) has achieved great success in reconstructing and rendering real-world scenes. To transfer the high rendering quality to generation tasks, a…
Parameter-efficient Fine-tuning in Hyperspherical Space for Open-vocabulary Semantic Segmentation
Zelin Peng, Zhengqin Xu, Zhilin Zeng +2
Open-vocabulary semantic segmentation seeks to label each pixel in an image with arbitrary text descriptions. Vision-language foundation models, especially CLIP, have recently emer…
AlignZeg: Mitigating Objective Misalignment for Zero-shot Semantic Segmentation
Jiannan Ge, Lingxi Xie, Hongtao Xie +4
A serious issue that harms the performance of zero-shot visual recognition is named objective misalignment, i.e., the learning objective prioritizes improving the recognition accur…
GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting
Chen Yang, Sikuang Li, Jiemin Fang +5
Reconstructing and rendering 3D objects from highly sparse views is of critical importance for promoting applications of 3D vision techniques and improving user experience. However…
Cascade-Zero123: One Image to Highly Consistent 3D with Self-Prompted Nearby Views
Yabo Chen, Jiemin Fang, Yuyang Huang +7
Synthesizing multi-view 3D from one single image is a significant but challenging task. Zero-1-to-3 methods have achieved great success by lifting a 2D latent diffusion model to th…
Segment Any 3D Gaussians
Jiazhong Cen, Jiemin Fang, Chen Yang +4
This paper presents SAGA (Segment Any 3D GAussians), a highly efficient 3D promptable segmentation method based on 3D Gaussian Splatting (3D-GS). Given 2D visual prompts as input,…
Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model
Zelin Peng, Zhengqin Xu, Zhilin Zeng +3
Parameter-efficient fine-tuning (PEFT) is an effective methodology to unleash the potential of large foundation models in novel scenarios with limited training data. In the compute…