On Unifying Video Generation and Camera Pose Estimation

Inspired by the emergent 3D capabilities in image generators, we explore whether video generators similarly exhibit 3D awareness. Using structure-from-motion (SfM) as a benchmark for 3D tasks, we investigate if intermediate features from OpenSora, a video generation model, can support camera pose estimation. We first examine native 3D awareness in video generation features by routing raw intermediate outputs to SfM-prediction modules like DUSt3R. Then, we explore the impact of fine-tuning on camera pose estimation to enhance 3D awareness. Results indicate that while video generator features have limited inherent 3D awareness, task-specific supervision significantly boosts their accuracy for camera pose estimation, resulting in competitive performance. The proposed unified model, named JOG3R, produces camera pose estimates with competitive quality without degrading video generation quality.

Free-viewpoint Human Animation with Pose-correlated Reference Selection

Diffusion-based human animation aims to animate a human character based on a source human image as well as driving signals such as a sequence of poses. Leveraging the generative capacity of diffusion model, existing approaches are able to generate high-fidelity poses, but struggle with significant viewpoint changes, especially in zoom-in/zoom-out scenarios where camera-character distance varies. This limits the applications such as cinematic shot type plan or camera control. We propose a pose-correlated reference selection diffusion network, supporting substantial viewpoint variations in human animation. Our key idea is to enable the network to utilize multiple reference images as input, since significant viewpoint changes often lead to missing appearance details on the human body. To eliminate the computational cost, we first introduce a novel pose correlation module to compute similarities between non-aligned target and source poses, and then propose an adaptive reference selection strategy, utilizing the attention map to identify key regions for animation generation. To train our model, we curated a large dataset from public TED talks featuring varied shots of the same character, helping the model learn synthesis for different perspectives. Our experimental results show that with the same number of reference images, our model performs favorably compared to the current SOTA methods under large viewpoint change. We further show that the adaptive reference selection is able to choose the most relevant reference regions to generate humans under free viewpoints.

GANFusion: Feed-Forward Text-to-3D with Diffusion in GAN Space

We train a feed-forward text-to-3D diffusion generator for human characters using only single-view 2D data for supervision. Existing 3D generative models cannot yet match the fidelity of image or video generative models. State-of-the-art 3D generators are either trained with explicit 3D supervision and are thus limited by the volume and diversity of existing 3D data. Meanwhile, generators that can be trained with only 2D data as supervision typically produce coarser results, cannot be text-conditioned, or must revert to test-time optimization. We observe that GAN- and diffusion-based generators have complementary qualities: GANs can be trained efficiently with 2D supervision to produce high-quality 3D objects but are hard to condition on text. In contrast, denoising diffusion models can be conditioned efficiently but tend to be hard to train with only 2D supervision. We introduce GANFusion, which starts by generating unconditional triplane features for 3D data using a GAN architecture trained with only single-view 2D data. We then generate random samples from the GAN, caption them, and train a text-conditioned diffusion model that directly learns to sample from the space of good triplane features that can be decoded into 3D objects.

Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation

While recent foundational video generators produce visually rich output, they still struggle with appearance drift, where objects gradually degrade or change inconsistently across frames, breaking visual coherence. We hypothesize that this is because there is no explicit supervision in terms of spatial tracking at the feature level. We propose Track4Gen, a spatially aware video generator that combines video diffusion loss with point tracking across frames, providing enhanced spatial supervision on the diffusion features. Track4Gen merges the video generation and point tracking tasks into a single network by making minimal changes to existing video generation architectures. Using Stable Video Diffusion as a backbone, Track4Gen demonstrates that it is possible to unify video generation and point tracking, which are typically handled as separate tasks. Our extensive evaluations show that Track4Gen effectively reduces appearance drift, resulting in temporally stable and visually coherent video generation. Project page: hyeonho99.github.io/track4gen

FloAt: Flow Warping of Self-Attention for Clothing Animation Generation

We propose a diffusion model-based approach, FloAtControlNet to generate cinemagraphs composed of animations of human clothing. We focus on human clothing like dresses, skirts and pants. The input to our model is a text prompt depicting the type of clothing and the texture of clothing like leopard, striped, or plain, and a sequence of normal maps that capture the underlying animation that we desire in the output. The backbone of our method is a normal-map conditioned ControlNet which is operated in a training-free regime. The key observation is that the underlying animation is embedded in the flow of the normal maps. We utilize the flow thus obtained to manipulate the self-attention maps of appropriate layers. Specifically, the self-attention maps of a particular layer and frame are recomputed as a linear combination of itself and the self-attention maps of the same layer and the previous frame, warped by the flow on the normal maps of the two frames. We show that manipulating the self-attention maps greatly enhances the quality of the clothing animation, making it look more natural as well as suppressing the background artifacts. Through extensive experiments, we show that the method proposed beats all baselines both qualitatively in terms of visual results and user study. Specifically, our method is able to alleviate the background flickering that exists in other diffusion model-based baselines that we consider. In addition, we show that our method beats all baselines in terms of RMSE and PSNR computed using the input normal map sequences and the normal map sequences obtained from the output RGB frames. Further, we show that well-established evaluation metrics like LPIPS, SSIM, and CLIP scores that are generally for visual quality are not necessarily suitable for capturing the subtle motions in human clothing animations.

HyperGAN-CLIP: A Unified Framework for Domain Adaptation, Image Synthesis and Manipulation

Generative Adversarial Networks (GANs), particularly StyleGAN and its variants, have demonstrated remarkable capabilities in generating highly realistic images. Despite their success, adapting these models to diverse tasks such as domain adaptation, reference-guided synthesis, and text-guided manipulation with limited training data remains challenging. Towards this end, in this study, we present a novel framework that significantly extends the capabilities of a pre-trained StyleGAN by integrating CLIP space via hypernetworks. This integration allows dynamic adaptation of StyleGAN to new domains defined by reference images or textual descriptions. Additionally, we introduce a CLIP-guided discriminator that enhances the alignment between generated images and target domains, ensuring superior image quality. Our approach demonstrates unprecedented flexibility, enabling text-guided image manipulation without the need for text-specific training data and facilitating seamless style transfer. Comprehensive qualitative and quantitative evaluations confirm the robustness and superior performance of our framework compared to existing methods.

Boosting Camera Motion Control for Video Diffusion Transformers

Recent advancements in diffusion models have significantly enhanced the quality of video generation. However, fine-grained control over camera pose remains a challenge. While U-Net-based models have shown promising results for camera control, transformer-based diffusion models (DiT)-the preferred architecture for large-scale video generation - suffer from severe degradation in camera motion accuracy. In this paper, we investigate the underlying causes of this issue and propose solutions tailored to DiT architectures. Our study reveals that camera control performance depends heavily on the choice of conditioning methods rather than camera pose representations that is commonly believed. To address the persistent motion degradation in DiT, we introduce Camera Motion Guidance (CMG), based on classifier-free guidance, which boosts camera control by over 400%. Additionally, we present a sparse camera control pipeline, significantly simplifying the process of specifying camera poses for long videos. Our method universally applies to both U-Net and DiT models, offering improved camera control for video generation tasks.

Learned Single-Pass Multitasking Perceptual Graphics for Immersive Displays

Immersive displays are advancing rapidly in terms of delivering perceptually realistic images by utilizing emerging perceptual graphics methods such as foveated rendering. In practice, multiple such methods need to be performed sequentially for enhanced perceived quality. However, the limited power and computational resources of the devices that drive immersive displays make it challenging to deploy multiple perceptual models simultaneously. We address this challenge by proposing a computationally-lightweight, text-guided, learned multitasking perceptual graphics model. Given RGB input images, our model outputs perceptually enhanced images by performing one or more perceptual tasks described by the provided text prompts. Our model supports a variety of perceptual tasks, including foveated rendering, dynamic range enhancement, image denoising, and chromostereopsis, through multitask learning. Uniquely, a single inference step of our model supports different permutations of these perceptual tasks at different prompted rates (i.e., mildly, lightly), eliminating the need for daisy-chaining multiple models to get the desired perceptual effect. We train our model on our new dataset of source and perceptually enhanced images, and their corresponding text prompts. We evaluate our model's performance on embedded platforms and validate the perceptual quality of our model through a user study. Our method achieves on-par quality with the state-of-the-art task-specific methods using a single inference step, while offering faster inference speeds and flexibility to blend effects at various intensities.

SuperGaussian: Repurposing Video Models for 3D Super Resolution

We present a simple, modular, and generic method that upsamples coarse 3D models by adding geometric and appearance details. While generative 3D models now exist, they do not yet match the quality of their counterparts in image and video domains. We demonstrate that it is possible to directly repurpose existing (pretrained) video models for 3D super-resolution and thus sidestep the problem of the shortage of large repositories of high-quality 3D training models. We describe how to repurpose video upsampling models, which are not 3D consistent, and combine them with 3D consolidation to produce 3D-consistent results. As output, we produce high quality Gaussian Splat models, which are object centric and effective. Our method is category agnostic and can be easily incorporated into existing 3D workflows. We evaluate our proposed SuperGaussian on a variety of 3D inputs, which are diverse both in terms of complexity and representation (e.g., Gaussian Splats or NeRFs), and demonstrate that our simple method significantly improves the fidelity of the final 3D models. Check our project website for details: supergaussian.github.io

SonicDiffusion: Audio-Driven Image Generation and Editing with Pretrained Diffusion Models

We are witnessing a revolution in conditional image synthesis with the recent success of large scale text-to-image generation methods. This success also opens up new opportunities in controlling the generation and editing process using multi-modal input. While spatial control using cues such as depth, sketch, and other images has attracted a lot of research, we argue that another equally effective modality is audio since sound and sight are two main components of human perception. Hence, we propose a method to enable audio-conditioning in large scale image diffusion models. Our method first maps features obtained from audio clips to tokens that can be injected into the diffusion model in a fashion similar to text tokens. We introduce additional audio-image cross attention layers which we finetune while freezing the weights of the original layers of the diffusion model. In addition to audio conditioned image generation, our method can also be utilized in conjuction with diffusion based editing methods to enable audio conditioned image editing. We demonstrate our method on a wide range of audio and image datasets. We perform extensive comparisons with recent methods and show favorable performance.