Related papers: In-Loop Filtering via Trained Look-Up Tables
We propose ReinFlow, a simple yet effective online reinforcement learning (RL) framework that fine-tunes a family of flow matching policies for continuous robotic control. Derived from rigorous RL theory, ReinFlow injects learnable noise…
Large Vision-Language Models (LVLMs) commonly follow a paradigm that projects visual features and then concatenates them with text tokens to form a unified sequence input for Large Language Models (LLMs). However, this paradigm leads to a…
Video compression is indispensable to most video analysis systems. Despite saving transportation bandwidth, it also deteriorates downstream video understanding tasks, especially at low-bitrate settings. To systematically investigate this…
Aiming at a drastic speedup for point-data embeddings at test time, we propose a new framework that uses a pair of multi-layer perceptron (MLP) and look-up table (LUT) to transform point-coordinate inputs into high-dimensional features.…
We introduce Lookup-Table Language Models (LookupLM), a method for scaling up the size of RNN language models with only a constant increase in the floating point operations, by increasing the expressivity of the embedding table. In…
Real-time high-accuracy optical flow estimation is a crucial component in various applications, including localization and mapping in robotics, object tracking, and activity recognition in computer vision. While recent learning-based…
Large Vision-Language Models (LVLMs) use their vision encoders to translate images into representations for downstream reasoning, but the encoders often underperform in domain-specific visual tasks such as medical image diagnosis or…
The deployment of large language models (LLMs) is often constrained by memory bandwidth, where the primary bottleneck is the cost of transferring model parameters from the GPU's global memory to its registers. When coupled with custom…
Efficient neural networks (NNs) leveraging lookup tables (LUTs) have demonstrated significant potential for emerging AI applications, particularly when deployed on field-programmable gate arrays (FPGAs) for edge computing. These…
Recent advances in implicit neural representations (INRs) have shown significant promise in modeling visual signals for various low-vision tasks including image super-resolution (ISR). INR-based ISR methods typically learn continuous…
Conventional hardware-friendly quantization methods, such as fixed-point or integer, tend to perform poorly at very low word sizes as their shrinking dynamic ranges cannot adequately capture the wide data distributions commonly seen in…
Significant advances in video compression system have been made in the past several decades to satisfy the nearly exponential growth of Internet-scale video traffic. From the application perspective, we have identified three major…
In this paper, we propose a distortion-aware loop filtering model to improve the performance of intra coding for 360$^o$ videos projected via equirectangular projection (ERP) format. To enable the awareness of distortion, our proposed…
We present an efficient finetuning methodology for neural-network filters which are applied as a postprocessing artifact-removal step in video coding pipelines. The fine-tuning is performed at encoder side to adapt the neural network to the…
Convolutional Neural Network (CNN) has an amount of parameter redundancy, filter pruning aims to remove the redundant filters and provides the possibility for the application of CNN on terminal devices. However, previous works pay more…
Implicit Neural Representation (INR) is an innovative approach for representing complex shapes or objects without explicitly defining their geometry or surface structure. Instead, INR represents objects as continuous functions. Previous…
A majority of methods for video frame interpolation compute bidirectional optical flow between adjacent frames of a video, followed by a suitable warping algorithm to generate the output frames. However, approaches relying on optical flow…
We consider the problem of reconstructing one-dimensional point sources from their Fourier measurements in a bounded interval $[-\Omega, \Omega]$. This problem is known to be challenging in the regime where the spacing of the sources is…
Learning binary representations of instances and classes is a classical problem with several high potential applications. In modern settings, the compression of high-dimensional neural representations to low-dimensional binary codes is a…
The integral image, an intermediate image representation, has found extensive use in multi-scale local feature detection algorithms, such as Speeded-Up Robust Features (SURF), allowing fast computation of rectangular features at constant…