Related papers: LASER: Layer-wise Scale Alignment for Training-Fre…

Video super-resolution (VSR) aims to restore a sequence of high-resolution (HR) frames from their low-resolution (LR) counterparts. Although some progress has been made, there are grand challenges to effectively utilize temporal dependency…

NVFP4 has recently emerged as an efficient 4-bit microscaling format for large language models (LLMs), offering superior numerical fidelity with native hardware support. However, existing methods often yield suboptimal performance due to…

Although neural radiance fields (NeRFs) have achieved triumphs in image novel view synthesis (NVS), LiDAR NVS remains largely unexplored. Previous LiDAR NVS methods employ a simple shift from image NVS methods while ignoring the dynamic…

Visually exploring in a real-world 4D spatiotemporal space freely in VR has been a long-term quest. The task is especially appealing when only a few or even single RGB cameras are used for capturing the dynamic scene. To this end, we…

Pareto-front optimization is crucial for addressing the multi-objective challenges in video streaming, enabling the identification of optimal trade-offs between conflicting goals such as bitrate, video quality, and decoding complexity. This…

Volumetric video streaming offers immersive 3D experiences but faces significant challenges due to high bandwidth requirements and latency issues in transmitting detailed content in real time. Traditional methods like point cloud streaming…

Depth acquisition, based on active illumination, is essential for autonomous and robotic navigation. LiDARs (Light Detection And Ranging) with mechanical, fixed, sampling templates are commonly used in today's autonomous vehicles. An…

Existing offline feed-forward methods for joint scene understanding and reconstruction on long image streams often repeatedly perform global computation over an ever-growing set of past observations, causing runtime and GPU memory to…

3D Gaussian Splatting (3DGS) has become a state-of-the-art framework for real-time, high-fidelity novel view synthesis. However, its substantial storage requirements and inherently unstructured representation pose challenges for deployment…

We present Stable Video Diffusion - a latent video diffusion model for high-resolution, state-of-the-art text-to-video and image-to-video generation. Recently, latent diffusion models trained for 2D image synthesis have been turned into…

The increasing demand for immersive AR/VR applications and spatial intelligence has heightened the need to generate high-quality scene-level and 360${\deg}$ panoramic video. However, most video diffusion models are constrained by limited…

Large transformer models are proving to be a powerful tool for 3D vision and novel view synthesis. However, the standard Transformer's well-known quadratic complexity makes it difficult to scale these methods to large scenes. To address…

Feed-forward 3D reconstruction models based on Vision Transformers can directly estimate scene geometry and camera poses from a small set of input images, but scaling them to video inputs with hundreds or thousands of frames remains…

We present StreamDEQ, a method that aims to infer frame-wise representations on videos with minimal per-frame computation. Conventional deep networks do feature extraction from scratch at each frame in the absence of ad-hoc solutions. We…

We propose VisFusion, a visibility-aware online 3D scene reconstruction approach from posed monocular videos. In particular, we aim to reconstruct the scene from volumetric features. Unlike previous reconstruction methods which aggregate…

The development of generalizable Novel View Synthesis (NVS) models is critically limited by the scarcity of large-scale training data featuring diverse and precise camera trajectories. While real-world captures are photorealistic, they are…

Managing chronic wounds is a global challenge that can be alleviated by the adoption of automatic systems for clinical wound assessment from consumer-grade videos. While 2D image analysis approaches are insufficient for handling the 3D…

Realistic reconstruction of dynamic 4D scenes from monocular videos is essential for understanding the physical world. Despite recent progress in neural rendering, existing methods often struggle to recover accurate 3D geometry and…

Recently, Sharma et al. suggested a method called Layer-SElective-Rank reduction (LASER) which demonstrated that pruning high-order components of carefully chosen LLM's weight matrices can boost downstream accuracy -- without any…

In streaming Reinforcement Learning (RL), transitions are observed and discarded immediately after a single update. While this minimizes resource usage for on-device applications, it makes agents notoriously sample-inefficient, since…