ControlVideo: Training-free Controllable Text-to-Video Generation

cs.CV 2025-01 conditional novelty 7.0 of 10

Interactive image editing can be cast as image-to-video generation: initializing from Stable Video Diffusion plus a new matching attention mechanism yields high-quality sketch, drag, and coarse-edit results with far l...

cs.CV 2024-12 conditional novelty 7.0 of 10

A distribution-matching, class-balanced selection method (CBS) improves incremental learning from unlabeled pools, beating random and standard active learning baselines on five datasets.

cs.CV 2026-08 conditional novelty 6.0 of 10

EmoWorld adds three training-free steering operators to a frozen video diffusion transformer that separately control atmosphere, affect-bearing cues, and temporal emotion transitions in generated videos.

cs.CV 2026-03 conditional novelty 6.0 of 10

SGC quantifies 3D geometric consistency of generated videos by measuring divergence among local camera poses estimated only on static background sub-regions.

cs.CV 2025-09 conditional novelty 6.0 of 10

A training-free video background replacement pipeline that keeps the foreground pixel-consistent by projecting refined latents through a deterministic reparameterization.

cs.CV 2025-09 conditional novelty 6.0 of 10

A diffusion-based disentanglement method that separates object content from domain style achieves state-of-the-art unsupervised cross-domain image retrieval on three benchmarks.

cs.CV 2025-08 conditional novelty 6.0 of 10

Single-image novel view synthesis is decomposed into panorama outpainting plus keyframe-conditioned video diffusion, producing loop-consistent scene tours.

cs.CV 2025-07 conditional novelty 6.0 of 10

EVS combines a text-to-image and a text-to-video diffusion model in a single denoising pass, improving frame quality and temporal consistency without retraining.

cs.CV 2025-07 conditional novelty 6.0 of 10

HairShifter transfers a reference hairstyle onto a person throughout a video by animating a high-quality anchor frame and using a gated decoder that preserves non-hair regions.

cs.CV 2025-07 conditional novelty 6.0 of 10

AnyI2V animates arbitrary conditional images with user-defined trajectories by injecting debiased diffusion features and aligning attention queries across frames, without training.

cs.CV 2025-06 conditional novelty 6.0 of 10

MotionEcho adaptively re-injects teacher-model guidance into few-step distilled video generators so reference motion can be copied at test time without training.

cs.CV 2025-06 reject novelty 6.0 of 10

A cross-attention control method that couples backgrounds across multiple generated images by blending LLM-extracted background and entity prompts with a time-varying weight optimized for background similarity and tex...

cs.CV 2025-06 conditional novelty 6.0 of 10

One diffusion transformer handles ID insert, swap, delete, stylization, propagation, and re-camera control in a single model using in-context token concatenation with task-aware positional encoding and bias.

cs.CV 2025-06 conditional novelty 6.0 of 10

By training a semantic expert and a LoRA-based detail expert, DCM reaches nearly teacher-level VBench scores with 4-step video sampling on HunyuanVideo and CogVideoX.

cs.CV 2025-05 conditional novelty 6.0 of 10

A training-free method combines mask normalization and temporal intrinsic denoising to improve trajectory control and perceptual quality in text-to-video diffusion.

cs.CV 2025-05 conditional novelty 6.0 of 10

EF-VI injects temporally expanded end-frame features into a transformer-based image-to-video diffusion model, improving video inbetweening quality over direct fine-tuning and bidirectional sampling baselines.

cs.GR 2025-05 conditional novelty 6.0 of 10

A video diffusion system that adds controllable weather effects to arbitrary videos and removes existing weather, trained on synthetic, generated, and auto-labeled real data.

cs.CV 2025-04 conditional novelty 6.0 of 10

AnimateAnywhere learns to animate the background of human videos directly from human pose sequences, using an epipolar-constrained 3D attention mechanism, and reports state-of-the-art results without camera trajectories.

cs.CV 2025-04 conditional novelty 6.0 of 10

Satellite-to-ground generation is extended from single images to consistent multi-view sequences by adding satellite-guided and satellite-temporal conditioning to a frozen latent diffusion model, with a new 100k-pair dataset.

cs.CV 2025-02 conditional novelty 6.0 of 10

AnyCharV is a two-stage diffusion method that places a reference character into a target video scene using pose and mask guidance, with a self-boosting stage that improves identity preservation.

cs.CV 2025-01 conditional novelty 6.0 of 10

A temporal attention purification and skip-connection rerouting method that separates motion learning from appearance learning in text-to-video diffusion model customization.

cs.CV 2025-01 conditional novelty 6.0 of 10

Video Depth Anything adapts Depth Anything V2 to produce temporally consistent depth for arbitrarily long videos using a temporal attention head, an optical-flow-free gradient loss, and key-frame-based stitching.

cs.CV 2025-01 conditional novelty 6.0 of 10

A 300M-parameter video generation model reaches about 5-dan level in Go and near-oracle robot control by predicting next frames and compact latent codes, with no search or reward.

cs.CV 2025-01 conditional novelty 6.0 of 10

TDM restores five kinds of video degradation with one ControlNet-fine-tuned Stable Diffusion model, using task prompts in training and windowed cross-frame attention plus DDIM inversion at inference for temporal consistency.

cs.CV 2025-01 conditional novelty 6.0 of 10

ACE trains a LoRA adapter on both conditional and unconditional noise predictions so that erased concepts are suppressed during both generation and text-guided editing.

cs.CV 2024-12 conditional novelty 6.0 of 10

A multi-granularity mixture-of-experts image restoration model that routes each degraded image to an expert using both degradation and granularity estimates, outperforming all-in-one baselines.

cs.CV 2024-12 conditional novelty 6.0 of 10

GaussianPainter produces 3D Gaussians from a point cloud and reference image in one forward pass by constraining Gaussian rotations with predicted surface normals.

cs.CV 2024-12 conditional novelty 6.0 of 10

Adaptive token routing with a lightweight refinement branch lets a ViT matting model run on full-resolution high-res images at about 12% of the memory of the ViTMatte baseline with only a small accuracy drop on Compos...

cs.CV 2024-12 conditional novelty 6.0 of 10

A cross-view attention module and hybrid training recipe let a frozen text-to-video model generate synchronized multi-camera videos from arbitrary viewpoints given only a text prompt and camera poses.

cs.CV 2024-12 conditional novelty 6.0 of 10

FCNet decouples facial colorization into per-component color codes, enabling controllable reference-based, automatic, and diverse colorization of face images.

cs.CV 2024-12 conditional novelty 6.0 of 10

MoViE distills a diffusion-based video editor into a single-step mobile model, achieving 12 fps on a Snapdragon 8 Gen 3 phone with modest quality loss.

cs.CV 2024-11 conditional novelty 6.0 of 10

ROSE uses patch-wise perception in a large multimodal model to predict dense masks and generate open-set category names without predefined prompts.

cs.CV 2024-11 conditional novelty 6.0 of 10

An auxiliary trajectory attention branch, added to temporal attention in video diffusion models, improves camera motion control precision while preserving generation quality.

cs.CV 2024-11 conditional novelty 6.0 of 10

A pipeline that uses multi-view diffusion-generated depth images as shape priors, fused with the partial point cloud via attention and confidence filtering, achieves state-of-the-art completion on custom single-view b...

cs.CV 2024-11 conditional novelty 6.0 of 10

FloAtControlNet animates clothing by flow-warping self-attention maps in a normal-map-conditioned ControlNet, improving temporal coherence and reducing background flicker.

cs.CV 2024-11 conditional novelty 6.0 of 10

A two-stage video generation system that converts camera, drag, and reference-video controls into unified optical flows, and adds a frequency-domain stabilizer to reduce flicker.

cs.GR 2024-11 conditional novelty 6.0 of 10

A text-guided system that animates a single raster sketch into a dynamic video by fine-tuning a text-to-video diffusion model and steering its attention maps with the input drawing.

cs.CV 2025-08 conditional novelty 5.0 of 10

Fine-tuning video generators on driving data can improve visual fidelity while degrading how accurately the model predicts the movement of cars and pedestrians.

cs.CV 2025-05 conditional novelty 5.0 of 10

A dual-stage fine-tuning recipe, norm tuning followed by a visual adapter, improves temporal consistency and text alignment in one-shot video editing, with a new 232-video benchmark.

cs.CV 2025-04 conditional novelty 5.0 of 10

Attention maps with high entropy correlate with video quality while low entropy maps carry structure, and this paper uses entropy-guided attention replacement to improve video generation and editing.

cs.CV 2024-12 conditional novelty 5.0 of 10

MMD-LoRA uses text-guided LoRA adapters and contrastive learning to adapt a depth estimator to unseen adverse weather conditions, setting new reported numbers on nuScenes and Oxford RobotCar.

cs.CV 2024-12 conditional novelty 5.0 of 10

A two-stage multi-task training method that trains auxiliary tasks equally in task-specific decoders and weights their shared-encoder gradients by uncertainty and gradient norm improves primary-task performance relati...

cs.CV 2024-12 conditional novelty 5.0 of 10

ReAtCo improves text-guided video editing by using attention-map gradients to place edited objects in user-specified regions and by re-injecting the original background during diffusion sampling.

cs.CV 2024-11 conditional novelty 5.0 of 10

VBench++ is a benchmark that scores text-to-video and image-to-video models on 16 quality dimensions plus trustworthiness, reporting human-alignment correlations for each.

cs.CV 2024-11 conditional novelty 5.0 of 10

A detector trained with feature contrastive and uncertainty classification losses improves open-set semi-supervised object detection, labeling unseen objects as unknown.

cs.CV 2026-08 conditional novelty 4.0 of 10

Combining separate face and hand models with a parametric body and Gaussian splatting enables multi-view-consistent upper-body avatars that can be re-animated with new expressions and gestures.

cs.CV 2025-08 conditional novelty 4.0 of 10

LongVie combines unified noise initialization, global control normalization, and multi-modal depth-plus-keypoint guidance to generate temporally consistent controllable videos of up to one minute.

eess.IV 2025-07 conditional novelty 4.0 of 10

A training-free Lagrangian motion magnification framework with periodic reference resetting and tissue-aware dual-mask control improves vascular pulsation visibility in endoscopic surgery videos.

cs.CV 2025-06 conditional novelty 4.0 of 10

DFVEdit edits videos by iteratively subtracting a conditional delta flow vector, the difference between the model's predictions under the target and source prompts, from the latent representation of the source video.

cs.CV 2025-01 reject novelty 4.0 of 10

DiffuEraser is a stable-diffusion video inpainting model that injects ProPainter priors via DDIM inversion and expands temporal receptive fields for long-sequence consistency.

cs.CV 2024-12 conditional novelty 4.0 of 10

MetricDepth adds a multi-range contrastive loss to monocular depth estimation, defining positive and negative feature pairs by ground-truth depth differences.

cs.CV 2024-12 conditional novelty 4.0 of 10

A ConvGRU temporal module with a geographic visibility mask raises BEV segmentation accuracy on nuScenes by about 1.3 to 1.8 IoU points over the Fiery baseline.

cs.CV 2024-12 conditional novelty 4.0 of 10

A mask-guided attention modulation framework for tuning-free multi-attribute video editing, built on Stable Diffusion, with keyframe feature propagation.

cs.CV 2024-12 conditional novelty 4.0 of 10

A masking and Jacobian projection technique discovers unsupervised semantic directions in diffusion model latent space, enabling region-local editing without fine-tuning.

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.

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).