15 papers
JointEdit3D: Feed-Forward 3D Scene Editing in a Unified Latent Space
Xinnan Zhu, Ruijie Xu, Jiayu Ying +4
Existing 3D scene editing methods typically rely on per-scene optimization over explicit 3D representations or cascaded edit-and-reconstruct pipelines, resulting in high test-time…
FLEG: Feed-Forward Language Embedded Gaussian Splatting from Any Views via Compact Semantic Representation
Qijian Tian, Xin Tan, Jiayu Ying +3
We present FLEG, a feed-forward network that reconstructs language-embedded 3D Gaussians from arbitrary views. Previous feed-forward language-embedded Gaussian reconstruction metho…
Explore with Long-term Memory: A Benchmark and Multimodal LLM-based Reinforcement Learning Framework for Embodied Exploration
Sen Wang, Bangwei Liu, Zhenkun Gao +4
An ideal embodied agent should possess lifelong learning capabilities to handle long-horizon and complex tasks, enabling continuous operation in general environments. This not only…
S2D: Sparse to Dense Lifting for 3D Reconstruction with Minimal Inputs
Yuzhou Ji, Qijian Tian, He Zhu +5
Explicit 3D representations have already become an essential medium for 3D simulation and understanding. However, the most commonly used point cloud and 3D Gaussian Splatting (3DGS…
Diffusion Implicit Policy for Unpaired Scene-aware Motion Synthesis
Jingyu Gong, Chong Zhang, Fengqi Liu +5
Scene-aware motion synthesis has been widely researched recently due to its numerous applications. Prevailing methods rely heavily on paired motion-scene data, while it is difficul…
PFDepth: Heterogeneous Pinhole-Fisheye Joint Depth Estimation via Distortion-aware Gaussian-Splatted Volumetric Fusion
Zhiwei Zhang, Ruikai Xu, Weijian Zhang +5
In this paper, we present the first pinhole-fisheye framework for heterogeneous multi-view depth estimation, PFDepth. Our key insight is to exploit the complementary characteristic…