8 papers
GaussianSelector: Lightweight Human-Guided Object Selection in 3D Gaussian Splatting with Graph Optimization
Baihan Yang, Tiexin Li, Yuheng Liu +4
Selecting a complete 3D object from a reconstructed scene with minimal user effort is essential for practical scene editing and embodied interaction. Existing 3DGS-based methods ei…
DSA: Dynamic Step Allocation for Fast Autoregressive Video Generation
Thanh-Tung Le, Yunhan Zhao, Menglei Chai +5
Video diffusion transformers have achieved state-of-the-art visual quality, but their high inference cost remains a major bottleneck for real-time applications. Recent distillation…
OmniRoam: World Wandering via Long-Horizon Panoramic Video Generation
Yuheng Liu, Xin Lin, Xinke Li +9
Modeling scenes using video generation models has garnered growing research interest in recent years. However, most existing approaches rely on perspective video models that synthe…
UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis
Thanh-Tung Le, Tuan Pham, Tung Nguyen +3
Novel view synthesis (NVS) seeks to render photorealistic, 3D-consistent images of a scene from unseen camera poses given only a sparse set of posed views. Existing deterministic n…
CoRA: A Collaborative Robust Architecture with Hybrid Fusion for Efficient Perception
Gong Chen, Chaokun Zhang, Pengcheng Lv +1
Collaborative perception has garnered significant attention as a crucial technology to overcome the perceptual limitations of single-agent systems. Many state-of-the-art (SOTA) met…
OPLoRA: Orthogonal Projection LoRA Prevents Catastrophic Forgetting during Parameter-Efficient Fine-Tuning
Yifeng Xiong, Xiaohui Xie
Low-Rank Adaptation (LoRA) enables efficient fine-tuning of large language models but suffers from catastrophic forgetting when learned updates interfere with the dominant singular…
GeoDiff: Geometry-Guided Diffusion for Metric Depth Estimation
Tuan Pham, Thanh-Tung Le, Xiaohui Xie +1
We introduce a novel framework for metric depth estimation that enhances pretrained diffusion-based monocular depth estimation (DB-MDE) models with stereo vision guidance. While ex…
Learning Unified Representation of 3D Gaussian Splatting
Yuelin Xin, Yuheng Liu, Xiaohui Xie +1
A well-designed vectorized representation is crucial for the learning systems natively based on 3D Gaussian Splatting. While 3DGS enables efficient and explicit 3D reconstruction,…