Related papers: PanoLora: Bridging Perspective and Panoramic Video…
Despite recent advances in photorealistic image generation through large-scale models like FLUX and Stable Diffusion v3, the practical deployment of these architectures remains constrained by their inherent intractability to parameter…
We present PanoPlane, an approach for high-fidelity sparse-view indoor novel view synthesis that reconstructs closed room geometry via panoramic scene completion. Unlike perspective-based methods that generate training views from limited…
We present a video generation model that accurately reproduces object motion, changes in camera viewpoint, and new content that arises over time. Existing video generation methods often fail to produce new content as a function of time…
Image editing has made great progress on planar images, but panoramic image editing remains underexplored. Due to their spherical geometry and projection distortions, panoramic images present three key challenges: boundary discontinuity,…
Diffusion models have emerged as effective tools for generating diverse and high-quality content. However, their capability in high-resolution image generation, particularly for panoramic images, still faces challenges such as visible seams…
Low-Rank Adaptation (LoRA) and its variants have delivered strong capability in Parameter-Efficient Transfer Learning (PETL) by minimizing trainable parameters and benefiting from reparameterization. However, their projection matrices…
Low-Rank Adaptation (LoRA) offers a cost-effective solution for fine-tuning large language models (LLMs), but it often produces overconfident predictions in data-scarce few-shot settings. To address this issue, several classical statistical…
Diffusion models have proven to be highly effective in image and video generation; however, they encounter challenges in the correct composition of objects when generating images of varying sizes due to single-scale training data. Adapting…
360{\deg} video provides an immersive experience for viewers, allowing them to freely explore the world by turning their head. However, creating high-quality 360{\deg} video content can be challenging, as viewers may miss important events…
Being able to edit panoramic images is crucial for creating realistic 360{\deg} visual experiences. However, existing perspective-based image editing methods fail to model the spatial structure of panoramas. Conventional cube-map…
Low-rank adaptation (LoRA) has achieved remarkable success in fine-tuning pre-trained vision transformers for various downstream tasks. Existing studies mainly focus on exploring more parameter-efficient strategies or more effective…
Continual Learning requires a model to learn multiple tasks in sequence while maintaining both stability:preserving knowledge from previously learned tasks, and plasticity:effectively learning new tasks. Gradient projection has emerged as…
Recovering 3D scenes from sparse views is a challenging task due to its inherent ill-posed problem. Conventional methods have developed specialized solutions (e.g., geometry regularization or feed-forward deterministic model) to mitigate…
Reconstructing dynamic 3D scenes (i.e., 4D geometry) from monocular video is an important yet challenging problem. Conventional multiview geometry-based approaches often struggle with dynamic motion, whereas recent learning-based methods…
In this paper, we tackle the challenging task of Panoramic Image-to-Image translation (Pano-I2I) for the first time. This task is difficult due to the geometric distortion of panoramic images and the lack of a panoramic image dataset with…
An image may convey a thousand words, but a video composed of hundreds or thousands of image frames tells a more intricate story. Despite significant progress in multimodal large language models (MLLMs), generating extended videos remains a…
A single Panorama can be drawn perspectively without distortions in arbitrary viewing directions and field-of-views when the camera position is at the origin. This is a key advantage in VR and virtual tour applications because it enables…
Video diffusion models are able to generate high-quality videos by learning strong spatial-temporal priors on large-scale datasets. In this paper, we aim to investigate whether such priors derived from a generative process are suitable for…
Continual learning for vision-language models has achieved remarkable performance through synthetic replay, where samples are generated using Stable Diffusion to regularize during finetuning and retain knowledge. However, real-world…
Recent advances in video generation enable a new paradigm for 3D scene creation: generating camera-controlled videos that simulate scene walkthroughs, then lifting them to 3D via feed-forward reconstruction techniques. This generative…