Pith. sign in

REVIEW 16 cited by

Adversarial Video Generation on Complex Datasets

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

arxiv 1907.06571 v2 pith:KO55Y7GS submitted 2019-07-15 cs.CV cs.LGstat.ML

classification cs.CVcs.LGstat.ML
keywords videokinetics-600synthesisadversarialcomplexdatasetdiscriminatorfidelity
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Generative models of natural images have progressed towards high fidelity samples by the strong leveraging of scale. We attempt to carry this success to the field of video modeling by showing that large Generative Adversarial Networks trained on the complex Kinetics-600 dataset are able to produce video samples of substantially higher complexity and fidelity than previous work. Our proposed model, Dual Video Discriminator GAN (DVD-GAN), scales to longer and higher resolution videos by leveraging a computationally efficient decomposition of its discriminator. We evaluate on the related tasks of video synthesis and video prediction, and achieve new state-of-the-art Fr\'echet Inception Distance for prediction for Kinetics-600, as well as state-of-the-art Inception Score for synthesis on the UCF-101 dataset, alongside establishing a strong baseline for synthesis on Kinetics-600.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 16 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers

    cs.CV 2025-07 conditional novelty 7.0 of 10

    A DiT-based portrait animation model transfers implicit facial expressions to one or more characters using a masked cross-attention mechanism, supported by a new multi-face dataset and benchmark.

  2. Test-Time Noise Guided Adaptation for Realistic Autoregressive Video Generation

    cs.CV 2026-07 conditional novelty 6.0 of 10

    TANGO avoids "terminal points" in autoregressive video generation by optimizing a LoRA adapter at test time until the model's one-step-ahead predicted noise looks like isotropic Gaussian noise.

  3. ELT: Elastic Looped Transformers for Visual Generation

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    Weight-shared looped transformers trained with intra-loop self-distillation match MaskGIT-class FID/FVD at roughly 4x fewer parameters and support any-time inference across loop counts.

  4. TARDIS STRIDE: A Spatio-Temporal Road Image Dataset and World Model for Autonomy

    cs.CV 2025-06 reject novelty 6.0 of 10

    TARDIS is a transformer world model trained on STRIDE, a graph-structured street-view dataset, with claimed abilities in controllable image generation, georeferencing, self-driving actions, and temporal simulation.

  5. Ingredients: Blending Custom Photos with Video Diffusion Transformers

    cs.CV 2025-01 conditional novelty 6.0 of 10

    Ingredients adds a mask-supervised identity router to a video diffusion transformer, enabling multi-person videos from a few reference photos without per-identity fine-tuning.

  6. ObjCtrl-2.5D: Training-free Object Control with Camera Poses

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A training-free method that lifts 2D object trajectories into camera poses with depth and uses a frozen camera-control video model to achieve more accurate and 3D-aware object motion, including rotation.

  7. Extended Field of View Analysis for VideoGAN-based Trajectory Generation

    cs.CV 2026-08 conditional novelty 5.0 of 10

    A video GAN trained on semantic top-down traffic videos generates 15–25 m field-of-view scenes whose speed, acceleration, spacing, and time-to-collision statistics resemble real Waymo data, with inference below 20 ms.

  8. Geometry-Aware Single-Image 4D Synthesis via Dense Trajectory Generation

    cs.CV 2025-12 conditional novelty 5.0 of 10

    A diffusion model generates dense 4D point trajectories from a single image, and a separate view-synthesis module renders them into novel-view videos.

  9. Seeing Voices: Generating A-Roll Video from Audio with Mirage

    cs.CV 2025-06 reject novelty 5.0 of 10

    Mirage generates photorealistic A-roll videos of people speaking directly from audio, using only joint self-attention over audio, text, and video tokens.

  10. LIA-X: Interpretable Latent Portrait Animator

    cs.CV 2025-08 conditional novelty 4.0 of 10

    Adding an L1 sparsity penalty to the motion dictionary of the LIA portrait animator produces disentangled, human-interpretable motion vectors that support controllable image and video editing and scale to roughly one ...

  11. Edge General Intelligence Through World Models and Agentic AI: Fundamentals, Solutions, and Challenges

    cs.LG 2025-08 conditional novelty 4.0 of 10

    A survey reviewing how world models and agentic AI could be combined to give edge devices predictive, proactive decision-making, with a taxonomy of methods, applications, and challenges.

  12. DTSGAN: Learning Dynamic Textures via Spatiotemporal Generative Adversarial Network

    cs.CV 2024-12 reject novelty 4.0 of 10

    DTSGAN adapts SinGAN-style multi-scale generation to video with 3D convolutions and a sliding-window data update, claiming improved dynamic texture synthesis and diversity.

  13. Video Diffusion Transformers are In-Context Learners

    cs.CV 2024-12 conditional novelty 4.0 of 10

    Concatenating multiple video clips into one input and fine-tuning a LoRA adapter lets a pretrained video diffusion transformer produce consistent multi-scene videos from a single prompt.

  14. Efficient Continuous Video Flow Model for Video Prediction

    cs.CV 2024-12 conditional novelty 4.0 of 10

    The paper adapts the authors' prior continuous-video-process framework to latent space, reporting state-of-the-art FVD on KTH, BAIR, Human3.6M, and UCF101 with fewer parameters and sampling steps.

  15. Continuous Video Process: Modeling Videos as Continuous Multi-Dimensional Processes for Video Prediction

    cs.CV 2024-12 conditional novelty 4.0 of 10

    CVP trains a network to reverse a continuous interpolation between past and future frames, reporting competitive FVD scores and 25-step sampling on KTH, BAIR, Human3.6M, and UCF101.

  16. Next Block Prediction: Video Generation via Semi-Autoregressive Modeling

    cs.CV 2025-02 conditional novelty 3.0 of 10

    NBP generates video rows in parallel with block-wise attention, achieving 11x faster inference and better FVD than next-token autoregressive models.

Pith tools