Physdreamer: Physics-based interaction with 3d objects via video generation

T Zhang, HX Yu, R Wu, BY Feng, C Zheng… - … on Computer Vision, 2024‏ - Springer
Realistic object interactions are crucial for creating immersive virtual experiences, yet
synthesizing realistic 3D object dynamics in response to novel interactions remains a …

Generative camera dolly: Extreme monocular dynamic novel view synthesis

B Van Hoorick, R Wu, E Ozguroglu, K Sargent… - … on Computer Vision, 2024‏ - Springer
Accurate reconstruction of complex dynamic scenes from just a single viewpoint continues to
be a challenging task in computer vision. Current dynamic novel view synthesis methods …

Dynamic gaussian marbles for novel view synthesis of casual monocular videos

C Stearns, A Harley, M Uy, F Dubost… - SIGGRAPH Asia 2024 …, 2024‏ - dl.acm.org
Gaussian splatting has become a popular representation for novel-view synthesis, exhibiting
clear strengths in efficiency, photometric quality, and compositional edibility. Following its …

MorpheuS: Neural Dynamic 360deg Surface Reconstruction from Monocular RGB-D Video

H Wang, J Wang, L Agapito - Proceedings of the IEEE/CVF …, 2024‏ - openaccess.thecvf.com
Neural rendering has demonstrated remarkable success in dynamic scene reconstruction.
Thanks to the expressiveness of neural representations prior works can accurately capture …

Recapture: Generative video camera controls for user-provided videos using masked video fine-tuning

DJ Zhang, R Paiss, S Zada, N Karnad… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Recently, breakthroughs in video modeling have allowed for controllable camera trajectories
in generated videos. However, these methods cannot be directly applied to user-provided …

DreamDrive: Generative 4D Scene Modeling from Street View Images

J Mao, B Li, B Ivanovic, Y Chen, Y Wang, Y You… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Synthesizing photo-realistic visual observations from an ego vehicle's driving trajectory is a
critical step towards scalable training of self-driving models. Reconstruction-based methods …

4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models

H Yu, C Wang, P Zhuang, W Menapace… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Existing dynamic scene generation methods mostly rely on distilling knowledge from pre-
trained 3D generative models, which are typically fine-tuned on synthetic object datasets. As …

D-NPC: Dynamic Neural Point Clouds for Non-Rigid View Synthesis from Monocular Video

M Kappel, F Hahlbohm, T Scholz, S Castillo… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Dynamic reconstruction and spatiotemporal novel-view synthesis of non-rigidly deforming
scenes recently gained increased attention. While existing work achieves impressive quality …

OSN: infinite representations of dynamic 3D scenes from monocular videos

Z Song, J Li, B Yang - arxiv preprint arxiv:2407.05615, 2024‏ - arxiv.org
It has long been challenging to recover the underlying dynamic 3D scene representations
from a monocular RGB video. Existing works formulate this problem into finding a single …

MoDGS: Dynamic Gaussian Splatting from Causually-captured Monocular Videos

Q Liu, Y Liu, J Wang, X Lv, P Wang, W Wang… - arxiv preprint arxiv …, 2024‏ - arxiv.org
In this paper, we propose MoDGS, a new pipeline to render novel-view images in dynamic
scenes using only casually captured monocular videos. Previous monocular dynamic NeRF …