REVIEW 8 cited by
Photorealistic Video Generation with 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
abstract
We present W.A.L.T, a transformer-based approach for photorealistic video generation via diffusion modeling. Our approach has two key design decisions. First, we use a causal encoder to jointly compress images and videos within a unified latent space, enabling training and generation across modalities. Second, for memory and training efficiency, we use a window attention architecture tailored for joint spatial and spatiotemporal generative modeling. Taken together these design decisions enable us to achieve state-of-the-art performance on established video (UCF-101 and Kinetics-600) and image (ImageNet) generation benchmarks without using classifier free guidance. Finally, we also train a cascade of three models for the task of text-to-video generation consisting of a base latent video diffusion model, and two video super-resolution diffusion models to generate videos of $512 \times 896$ resolution at $8$ frames per second.
Forward citations
Cited by 8 Pith papers
-
ActionParty: Multi-Subject Action Binding in Generative Video Games
ActionParty binds discrete actions to individual subjects in a single generated video by jointly modeling subject state tokens and video latents, controlling up to seven players across 46 Melting Pot games.
-
WaiT for the Signal: Simple Frequency-Aware Flow-Matching
WaiT delays high-frequency wavelet bands in flow-matching image generation until coarse structure emerges, improving quality and cutting compute, with a reported SOTA FID of 1.30 on ImageNet 512.
-
Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments
Flow equivariant world models use a latent memory that shifts with the agent and with inferred object motion, giving stable long-horizon prediction under partial observability.
-
MambaVideo for Discrete Video Tokenization with Channel-Split Quantization
A Mamba-based hierarchical video tokenizer with channel-split quantization achieves state-of-the-art reconstruction and generation scores while preserving token count.
-
Populate-A-Scene: Affordance-Aware Human Video Generation
A fine-tuned text-to-video model inserts a person into a scene and generates an interaction video without bounding boxes or pose input, and its attention maps reveal a latent sense of affordance.
-
HiWave: Training-Free High-Resolution Image Generation via Wavelet-Based Diffusion Sampling
A training-free diffusion sampling pipeline combines patch-wise DDIM inversion with wavelet-domain frequency guidance to generate coherent 4096x4096 images from SDXL.
-
VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignment
A VGGT-based pointwise reprojection reward with geometry-aware sampling improves video geometric consistency via SFT/DPO and causal test-time search.
-
Leveraging Pre-Trained Visual Models for AI-Generated Video Detection
Pre-trained SigLIP/VideoMAE features with a linear probe or nearest-neighbor distance separate real videos from text-to-video model outputs, reaching about 90% average F1 on the new VID-AID benchmark, but much lower o...
Discussion (0). Sign in to comment.