GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions

cs.CV 2025-06 conditional novelty 8.0 of 10

RDPO builds preference pairs by reverse-sampling real video latents with a pre-trained generator, then fine-tunes with Flow-DPO, improving physics consistency metrics on two video models.

cs.CV 2026-02 conditional novelty 7.0 of 10

Causal Forcing uses an autoregressive teacher for ODE initialization in diffusion distillation to close the causal attention gap and deliver better real-time video generation than Self Forcing.

cs.CV 2025-04 conditional novelty 7.0 of 10

BadVideo shows that text-to-video models can be backdoored by poisoning fine-tuning data with temporally distributed malicious content that evades frame-based moderation.

cs.CV 2026-04 conditional novelty 6.0 of 10

SymphoMotion jointly controls camera trajectories and depth-aware object dynamics inside one video diffusion model, supported by the new RealCOD-25K real-world paired-motion dataset.

cs.CV 2025-09 conditional novelty 6.0 of 10

A video editor trained on randomly distorted objects, then steered by adaptive noise at inference, is claimed to surpass dedicated and unified editors across eight tasks with far less training.

cs.CV 2025-09 conditional novelty 6.0 of 10

NSD uses a contrastively learned style embedding from the input image itself, fed through a second cross-attention branch, to make diffusion-based inpainting results match the surrounding scene's style.

cs.CV 2025-08 conditional novelty 6.0 of 10

MiraMo turns a static image into a video using a linear-attention transformer that learns inter-frame motion residuals, with DCT-based noise refinement and a user-controllable dynamics knob.

cs.CV 2025-05 conditional novelty 6.0 of 10

SAGE edits real images with text by using self-attention maps from inverse DDIM as guidance, which preserves unedited regions without per-image optimization.

cs.CV 2025-05 conditional novelty 6.0 of 10

FreePCA improves training-free long video generation by projecting global and local attention features into PCA space, selecting consistent appearance components from global and motion components from local, then prog...

cs.HC 2025-04 conditional novelty 6.0 of 10

MV-Crafter generates beat-synchronized music videos from music and a text theme by combining LLM-based scripting, diffusion video generation, and a dynamic beat-matching warping algorithm.

cs.CV 2025-01 conditional novelty 6.0 of 10

OmniPhysGS lets each Gaussian in a 3D scene select from 12 expert material models, supervised by a text-to-video diffusion model, to generate dynamics for multiple materials.

cs.CV 2024-12 conditional novelty 6.0 of 10

Controlled scaling shows a 2.3B self-attention U-ViT matches or slightly outperforms SDXL U-Net and larger cross-attention DiT variants, while long captions and larger datasets improve text-image alignment.

cs.CV 2024-12 conditional novelty 6.0 of 10

BrushEdit couples a multimodal language model and an object detector with a single arbitrary-mask inpainting model to turn free-form text instructions into interactive, multi-turn image edits.

cs.CV 2024-12 conditional novelty 6.0 of 10

TIV-Diffusion adds object-centric slot alignment to a diffusion-based image-to-video generator and reports improved alignment and temporal-consistency metrics on MNIST, CATER, and Bridge datasets.

cs.HC 2024-12 conditional novelty 6.0 of 10

VSD2M, a 2.09 million sample bilingual sticker dataset with animated GIFs, plus a Spatial Temporal Interaction layer, improves animated sticker generation over standard video diffusion baselines.

cs.CV 2024-12 conditional novelty 6.0 of 10

An iterative design-generate-redesign pipeline with four specialized LLM agents and self-routing correction improves compositional text-to-video generation on T2V-CompBench, with the largest gains in object numeracy.

cs.CV 2024-12 conditional novelty 6.0 of 10

Diffusion-conditioned denoising trains a video tokenizer whose features support both video question answering and text-to-video generation in a single LLM.

cs.CV 2024-12 conditional novelty 6.0 of 10

PainterNet is a diffusion-model plugin that uses local prompts, attention supervision, and diverse masks to improve text-consistent image inpainting.

cs.CV 2024-11 conditional novelty 6.0 of 10

I2VControl unifies camera, drag, and brush controls into a single point-trajectory-based adapter for image-to-video diffusion models, enabling conflict-free combined motion control.

cs.CV 2026-07 conditional novelty 5.0 of 10

ABot-World-0 claims real-time, long-horizon interactive world rollout on a single desktop GPU using raw keyboard actions, distillation, and low-bit inference, but the results cannot yet be independently checked becaus...

cs.CV 2025-06 conditional novelty 5.0 of 10

AIGVEval combines BLIP, 3D Swin Transformer, and SlowFast features with a LoRA-tuned LLM to predict AI-generated video quality, hitting second place on the NTIRE 2025 Track 2 leaderboard.

eess.IV 2025-05 conditional novelty 5.0 of 10

Decoder-side ClipSeg segmentation and content-adaptive diffusion steps improve MISC-based ultra-low-bitrate generative image compression in perceptual quality and speed.

cs.CV 2025-04 conditional novelty 5.0 of 10

VGDFR speeds up video diffusion generation by adaptively merging low-motion frames in latent space and adjusting positional embeddings, achieving up to 3x faster inference with modest quality changes.

cs.CV 2025-01 conditional novelty 5.0 of 10

A feature cache and gating mechanism that aggregates neighboring layer outputs in a video diffusion transformer improves temporal coherence and spatial accuracy.

cs.RO 2026-07 conditional novelty 4.0 of 10

Physical intelligence needs an embodied brain that reasons over interventions and emits capability requests, grounded by a physical harness and shared experience contracts rather than direct actuator policies.

cs.CV 2025-07 conditional novelty 4.0 of 10

SSD is a diffusion score-distillation loss for text-guided 2D and 3D editing that combines a CFG cross-prompt term, a null-text cross-trajectory regularizer, and a prompt-enhancement term to stabilize edits.

cs.CV 2025-06 conditional novelty 4.0 of 10

MTADiffusion improves text-guided object inpainting by training on a new 5M-image mask-text dataset with edge prediction and style-consistency losses.

cs.CV 2025-06 conditional novelty 4.0 of 10

PAROAttention permutes tokens along frame, height, and width axes to make visual attention block-wise, enabling sparse and INT8/INT4 quantized attention with near-baseline generation quality.

cs.CV 2025-04 conditional novelty 4.0 of 10

A survey that divides interactive generative video research into five modules: generation, control, memory, dynamics, and intelligence.

cs.CV 2025-02 reject novelty 4.0 of 10

HuViDPO claims the first DPO-based alignment for text-to-video generation, but its loss reduces to the known DPO-SDXL objective and the evaluation is not reproducible.

cs.CV 2024-12 conditional novelty 4.0 of 10

A diffusion transformer with joint attention over all camera views and frames, a lightweight BEV controller, and a re-weighted object loss reports state-of-the-art multi-view driving video generation (FVD 37.8 on nuScenes).