REVIEW 10 cited by
Diffusion$^2$: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
abstract
Recent advancements in 3D generation are predominantly propelled by improvements in 3D-aware image diffusion models. These models are pretrained on Internet-scale image data and fine-tuned on massive 3D data, offering the capability of producing highly consistent multi-view images. However, due to the scarcity of synchronized multi-view video data, it remains challenging to adapt this paradigm to 4D generation directly. Despite that, the available video and 3D data are adequate for training video and multi-view diffusion models separately that can provide satisfactory dynamic and geometric priors respectively. To take advantage of both, this paper presents Diffusion$^2$, a novel framework for dynamic 3D content creation that reconciles the knowledge about geometric consistency and temporal smoothness from these models to directly sample dense multi-view multi-frame images which can be employed to optimize continuous 4D representation. Specifically, we design a simple yet effective denoising strategy via score composition of pretrained video and multi-view diffusion models based on the probability structure of the target image array. To alleviate the potential conflicts between two heterogeneous scores, we further introduce variance-reducing sampling via interpolated steps, facilitating smooth and stable generation. Owing to the high parallelism of the proposed image generation process and the efficiency of the modern 4D reconstruction pipeline, our framework can generate 4D content within few minutes. Notably, our method circumvents the reliance on expensive and hard-to-scale 4D data, thereby having the potential to benefit from the scaling of the foundation video and multi-view diffusion models. Extensive experiments demonstrate the efficacy of our proposed framework in generating highly seamless and consistent 4D assets under various types of conditions.
Forward citations
Cited by 10 Pith papers
-
Wonderland: Navigating 3D Scenes from a Single Image
A feed-forward pipeline reconstructs 3D Gaussian scenes from single images by regressing 3DGS directly from camera-conditioned video diffusion latents.
-
MVISTA-4D: View-Consistent 4D World Model with Test-Time Action Inference for Robotic Manipulation
A geometry-consistent multi-view RGBD 4D world model for robot manipulation, whose actions are recovered by test-time optimization of a learned trajectory latent, outperforming single- and dual-view world-model baseli...
-
CharacterShot: Controllable and Consistent 4D Character Animation
A new pipeline generates pose-controlled, view-consistent 4D character animations from one reference image and a 2D pose sequence, backed by a new 13,115-character dataset and benchmark.
-
4DVD: Cascaded Dense-view Video Diffusion Model for High-quality 4D Content Generation
A two-stage cascaded video diffusion model generates 16-view consistent videos from a monocular video, enabling higher-quality 4D content reconstruction.
-
Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis
A video-to-4D model that encodes mesh animations into compact Gaussian variation latents and diffuses them conditioned on the video and a canonical Gaussian splat.
-
AR4D: Autoregressive 4D Generation from Monocular Videos
AR4D generates 4D content from monocular video by autoregressively deforming frame-wise 3D Gaussians, with progressive pseudo-view supervision from a pre-trained reconstruction model.
-
DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving
DrivingRecon predicts 4D Gaussians of street scenes from surround-view video in one forward pass, using a novel Prune and Dilate Block to reduce redundant overlapping points.
-
CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models
CAT4D uses a multi-view video diffusion model to convert monocular video into multi-view video and reconstruct a dynamic 3D Gaussian scene, with competitive results on 4D reconstruction benchmarks.
-
AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers
AC3D improves camera control in video diffusion transformers by conditioning only early denoising steps and the first 8 of 32 blocks, and by adding 20K static-camera dynamic videos to training.
-
DevilSight: Augmenting Monocular Human Avatar Reconstruction through a Virtual Perspective
A monocular human avatar reconstruction method generates pseudo back-view videos with a fine-tuned diffusion model and uses them as extra training data for a 3D Gaussian avatar.
Discussion (0). Continue with ORCID to comment.