REVIEW 7 cited by
HumanDiT: Pose-Guided Diffusion Transformer for Long-form Human Motion Video Generation
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
read the original abstract
Human motion video generation has advanced significantly, while existing methods still struggle with accurately rendering detailed body parts like hands and faces, especially in long sequences and intricate motions. Current approaches also rely on fixed resolution and struggle to maintain visual consistency. To address these limitations, we propose HumanDiT, a pose-guided Diffusion Transformer (DiT)-based framework trained on a large and wild dataset containing 14,000 hours of high-quality video to produce high-fidelity videos with fine-grained body rendering. Specifically, (i) HumanDiT, built on DiT, supports numerous video resolutions and variable sequence lengths, facilitating learning for long-sequence video generation; (ii) we introduce a prefix-latent reference strategy to maintain personalized characteristics across extended sequences. Furthermore, during inference, HumanDiT leverages Keypoint-DiT to generate subsequent pose sequences, facilitating video continuation from static images or existing videos. It also utilizes a Pose Adapter to enable pose transfer with given sequences. Extensive experiments demonstrate its superior performance in generating long-form, pose-accurate videos across diverse scenarios.
Forward citations
Cited by 7 Pith papers
-
ViDS: Video Diffusion Shader using 3D Face Tracking
Fine-tuning a video diffusion model on dense 3DMM normal maps from Pixel3DMM lets a single portrait photo be animated with a driving video's expressions and pose, surpassing landmark- and latent-based portrait animati...
-
AHOY! Animatable Humans under Occlusion from YouTube Videos with Gaussian Splatting and Video Diffusion Priors
Identity-finetuned video diffusion plus RF-Inversion can supply multi-view body supervision that lets 3D Gaussian avatars be completed and animated from heavily occluded monocular video.
-
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.
-
DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformers
A diffusion transformer model generates human-product demonstration videos from paired human and product images while preserving both identities through masked cross-attention and motion template guidance.
-
InfinityHuman: Towards Long-Term Audio-Driven Human
A coarse-to-fine audio-driven animation framework that uses pose-guided refinement and hand-specific reward learning to generate long, identity-stable talking videos.
-
FramePrompt: In-context Controllable Animation with Zero Structural Changes
FramePrompt turns character animation into a video-continuation task by concatenating reference image, skeleton frames, and target frames into one sequence, then training the pretrained Wan-I2V model to generate only ...
-
iDiT-HOI: Inpainting-based Hand Object Interaction Reenactment via Video Diffusion Transformer
A two-stage inpainting-based video diffusion transformer that reuses pretrained attention to reenact hand-object interactions with novel objects, reporting SOTA performance on Re-HOLD and a new in-the-wild dataset.
Discussion (0). Continue with ORCID to comment.