8 papers
tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction
Chen Wang, Hao Tan, Wang Yifan +6
We propose tttLRM, a novel large 3D reconstruction model that leverages a Test-Time Training (TTT) layer to enable long-context, autoregressive 3D reconstruction with linear comput…
Zero-shot Reconstruction of In-Scene Object Manipulation from Video
Dixuan Lin, Tianyou Wang, Zhuoyang Pan +3
We build the first system to address the problem of reconstructing in-scene object manipulation from a monocular RGB video. It is challenging due to ill-posed scene reconstruction,…
DIMO: Diverse 3D Motion Generation for Arbitrary Objects
Linzhan Mou, Jiahui Lei, Chen Wang +2
We present DIMO, a generative approach capable of generating diverse 3D motions for arbitrary objects from a single image. The core idea of our work is to leverage the rich priors…
StereoDiff: Stereo-Diffusion Synergy for Video Depth Estimation
Haodong Li, Chen Wang, Jiahui Lei +2
Recent video depth estimation methods achieve great performance by following the paradigm of image depth estimation, i.e., typically fine-tuning pre-trained video diffusion models…
Extrapolated Urban View Synthesis Benchmark
Xiangyu Han, Zhen Jia, Boyi Li +8
Photorealistic simulators are essential for the training and evaluation of vision-centric autonomous vehicles (AVs). At their core is Novel View Synthesis (NVS), a crucial capabili…
RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion
Jaidev Shriram, Alex Trevithick, Lingjie Liu +1
We introduce RealmDreamer, a technique for generating forward-facing 3D scenes from text descriptions. Our method optimizes a 3D Gaussian Splatting representation to match complex…