Related papers: Alignment is All You Need: A Training-free Augment…

There are many recent research efforts to fine-tune a pre-trained generator with a few target images to generate images of a novel domain. Unfortunately, these methods often suffer from overfitting or under-fitting when fine-tuned with a…

Transferring human motion and appearance between videos of human actors remains one of the key challenges in Computer Vision. Despite the advances from recent image-to-image translation approaches, there are several transferring contexts…

Styled motion in-betweening is crucial for computer animation and gaming. However, existing methods typically encode motion styles by modeling whole-body motions, often overlooking the representation of individual body parts. This…

Creating and updating pixel art character sprites with many frames spanning different animations and poses takes time and can quickly become repetitive. However, that can be partially automated to allow artists to focus on more creative…

Inferring 3D human pose from 2D images is a challenging and long-standing problem in the field of computer vision with many applications including motion capture, virtual reality, surveillance or gait analysis for sports and medicine. We…

Devising intelligent agents able to live in an environment and learn by observing the surroundings is a longstanding goal of Artificial Intelligence. From a bare Machine Learning perspective, challenges arise when the agent is prevented…

Advancements in neural implicit representations and differentiable rendering have markedly improved the ability to learn animatable 3D avatars from sparse multi-view RGB videos. However, current methods that map observation space to…

Recent diffusion-based human image animation techniques have demonstrated impressive success in synthesizing videos that faithfully follow a given reference identity and a sequence of desired movement poses. Despite this, there are still…

Humans excel in navigating diverse, complex environments with agile motor skills, exemplified by parkour practitioners performing dynamic maneuvers, such as climbing up walls and jumping across gaps. Reproducing these agile movements with…

Greyscale image colorization for applications in image restoration has seen significant improvements in recent years. Many of these techniques that use learning-based methods struggle to effectively colorize sparse inputs. With the…

In computer graphics, animation compression is essential for efficient storage, streaming and reproduction of animated meshes. Previous work has presented efficient techniques for compression by deriving skinning transformations and weights…

Temporal consistency is critical in video prediction to ensure that outputs are coherent and free of artifacts. Traditional methods, such as temporal attention and 3D convolution, may struggle with significant object motion and may not…

Creating scenes for captured motions that achieve realistic human-scene interaction is crucial for 3D animation in movies or video games. As character motion is often captured in a blue-screened studio without real furniture or objects in…

In this paper, we introduce GaussianMotion, a novel human rendering model that generates fully animatable scenes aligned with textual descriptions using Gaussian Splatting. Although existing methods achieve reasonable text-to-3D generation…

Filmmaking and animation production often require sophisticated techniques for coordinating camera transitions and object movements, typically involving labor-intensive real-world capturing. Despite advancements in generative AI for video…

3D characters are essential to modern creative industries, but making them animatable often demands extensive manual work in tasks like rigging and skinning. Existing automatic rigging tools face several limitations, including the necessity…

In this work we present an adversarial training algorithm that exploits correlations in video to learn --without supervision-- an image generator model with a disentangled latent space. The proposed methodology requires only a few…

We introduce a new method for learning a generative model of articulated 3D animal motions from raw, unlabeled online videos. Unlike existing approaches for 3D motion synthesis, our model requires no pose annotations or parametric shape…

Accurate estimation of 3D human motion from monocular video requires modeling both kinematics (body motion without physical forces) and dynamics (motion with physical forces). To demonstrate this, we present SimPoE, a Simulation-based…

We consider the problem of image-to-video translation, where an input image is translated into an output video containing motions of a single object. Recent methods for such problems typically train transformation networks to generate…