Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Diffusion Priors for Dynamic View Synthesis from Monocular Videos

About

Dynamic novel view synthesis aims to capture the temporal evolution of visual content within videos. Existing methods struggle to distinguishing between motion and structure, particularly in scenarios where camera poses are either unknown or constrained compared to object motion. Furthermore, with information solely from reference images, it is extremely challenging to hallucinate unseen regions that are occluded or partially observed in the given videos. To address these issues, we first finetune a pretrained RGB-D diffusion model on the video frames using a customization technique. Subsequently, we distill the knowledge from the finetuned model to a 4D representations encompassing both dynamic and static Neural Radiance Fields (NeRF) components. The proposed pipeline achieves geometric consistency while preserving the scene identity. We perform thorough experiments to evaluate the efficacy of the proposed method qualitatively and quantitatively. Our results demonstrate the robustness and utility of our approach in challenging cases, further advancing dynamic novel view synthesis.

Chaoyang Wang, Peiye Zhuang, Aliaksandr Siarohin, Junli Cao, Guocheng Qian, Hsin-Ying Lee, Sergey Tulyakov• 2024

Related benchmarks

TaskDatasetResultRank
Novel View SynthesisiPhone DyCheck 7 scenes 2x resolution--
31
Novel View SynthesisiPhone dataset
SSIM0.559
23
4D ReconstructionDyCheck (test)--
21
Showing 3 of 3 rows

Other info

Follow for update