Related papers: LiteVoxel: Low-memory Intelligent Thresholding for…

Parameter-efficient fine-tuning (PEFT) has emerged as a popular solution for adapting pre-trained Vision Transformer (ViT) models to downstream applications by updating only a small subset of parameters. While current PEFT methods have…

We extend the recently proposed sparse voxel rasterization paradigm to the task of high-fidelity surface reconstruction by integrating Signed Distance Function (SDF), named SVRecon. Unlike 3D Gaussians, sparse voxels are spatially…

This paper presents L-VITeX, a lightweight visual intuition system for terrain exploration designed for resource-constrained robots and swarms. L-VITeX aims to provide a hint of Regions of Interest (RoIs) without computationally expensive…

This paper proposes a novel, resource-efficient approach to Visual Speech Recognition (VSR) leveraging speech representations produced by any trained Automatic Speech Recognition (ASR) model. Moving away from the resource-intensive trends…

Visual relocalization is a key technique to autonomous driving, robotics, and virtual/augmented reality. After decades of explorations, absolute pose regression (APR), scene coordinate regression (SCR), and hierarchical methods (HMs) have…

Multi-organ segmentation of 3D medical images is fundamental with meaningful applications in various clinical automation pipelines. Although deep learning has achieved superior performance, the time and memory consumption of segmenting the…

Recent advancements in automatic speech recognition (ASR) have achieved notable progress, whereas robustness in noisy environments remains challenging. While speech enhancement (SE) front-ends are widely used to mitigate noise as a…

Road segmentation is a fundamental perception task for autonomous driving and intelligent robotic systems, requiring both high accuracy and real-time inference, especially for deployment on resource-constrained edge devices. Existing…

Fully finetuning foundation language models (LMs) with billions of parameters is often impractical due to high computational costs, memory requirements, and the risk of overfitting. Although methods like low-rank adapters help address these…

This paper presents LiteVLoc, a hierarchical visual localization framework that uses a lightweight topo-metric map to represent the environment. The method consists of three sequential modules that estimate camera poses in a coarse-to-fine…

Neural Radiance Field (NeRF) is a popular method in data-driven 3D reconstruction. Given its simplicity and high quality rendering, many NeRF applications are being developed. However, NeRF's big limitation is its slow speed. Many attempts…

The recently proposed SparseFormer architecture provides an alternative approach to visual understanding by utilizing a significantly lower number of visual tokens via adjusting RoIs, greatly reducing computational costs while still…

Recent works on parameter-efficient transfer learning (PETL) show the potential to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. However, since they usually insert new…

Visual AutoRegressive (VAR) models based on next-scale prediction enable efficient hierarchical generation, yet the inference cost grows quadratically at high resolutions. We observe that the computationally intensive later scales…

Volumetric data compression is critical in fields like medical imaging, scientific simulation, and entertainment. We introduce a structure-free neural compression method combining Fourierfeature encoding with selective voxel sampling,…

We present Reversible Vision Transformers, a memory efficient architecture design for visual recognition. By decoupling the GPU memory requirement from the depth of the model, Reversible Vision Transformers enable scaling up architectures…

Small animal PET scanners require high spatial resolution and good sensitivity. To reconstruct high-resolution images in 3D-PET, iterative methods, such as OSEM, are superior to analytical reconstruction algorithms, although their high…

A considerable limitation of employing sparse voxels octrees (SVOs) as a model format for ray tracing has been that the octree data structure is inherently static. Due to traversal algorithms' dependence on the strict hierarchical structure…

High-resolution images enable neural networks to learn richer visual representations. However, this improved performance comes at the cost of growing computational complexity, hindering their usage in latency-sensitive applications. As not…

We present a new dataset condensation framework termed Squeeze, Recover and Relabel (SRe$^2$L) that decouples the bilevel optimization of model and synthetic data during training, to handle varying scales of datasets, model architectures…