Related papers: LoGeR: Long-Context Geometric Reconstruction with …
Recent advancements in multi-view scene reconstruction have been significant, yet existing methods face limitations when processing streams of input images. These methods either rely on time-consuming offline optimization or are restricted…
Prevailing High Dynamic Range (HDR) video reconstruction methods are fundamentally trapped in a fragile alignment-and-fusion paradigm. While explicit spatial alignment can successfully recover fine details in controlled environments, it…
Online 3D reconstruction requires estimating camera pose and scene geometry under strict causal and bounded-memory constraints. Existing methods often suffer from drift, jitter, or collapse on long sequences. We trace these failures to a…
Long-term memory is essential for conversational agents to maintain coherence, track persistent tasks, and provide personalized interactions across extended dialogues. However, existing approaches as Retrieval-Augmented Generation (RAG) and…
Nowadays, transformer networks have demonstrated superior performance in many computer vision tasks. In a multi-view 3D reconstruction algorithm following this paradigm, self-attention processing has to deal with intricate image tokens…
Transformer-based 3D reconstruction has emerged as a powerful paradigm for recovering geometry and appearance from multi-view observations, offering strong performance across challenging visual conditions. As these models scale to larger…
Streaming 3D perception is well suited to robotics and augmented reality, where long visual streams must be processed efficiently and consistently. Recent recurrent models offer a promising solution by maintaining fixed-size states and…
Computing geodesic distances on 3D surfaces is fundamental to many tasks in 3D vision and geometry processing, with deep connections to tasks such as shape correspondence. Recent learning-based methods achieve strong performance but rely on…
This work presents ViGeo, a feed-forward foundation model for recovering spatially dense and temporally consistent geometry from video sequences. Built upon a plain transformer architecture without task-specific architectural modifications,…
Large Language Models (LLMs) encounter significant performance bottlenecks in long-sequence tasks due to the computational complexity and memory overhead inherent in the self-attention mechanism. To address these challenges, we introduce…
Recent feed-forward reconstruction models like VGGT and $\pi^3$ achieve impressive reconstruction quality but cannot process streaming videos due to quadratic memory complexity, limiting their practical deployment. While existing streaming…
3D reconstruction from multi-view images is a core challenge in computer vision. Recently, feed-forward methods have emerged as efficient and robust alternatives to traditional per-scene optimization techniques. Among them, state-of-the-art…
Training and serving long-context large language models (LLMs) incurs substantial overhead. To address this, two critical steps are often required: a pretrained LLM typically undergoes a separate stage for context length extension by…
Most modern deep learning-based multi-view 3D reconstruction techniques use RNNs or fusion modules to combine information from multiple images after independently encoding them. These two separate steps have loose connections and do not…
Recent advances in 4D Gaussian Splatting (4DGS) have extended the high-speed rendering capability of 3D Gaussian Splatting (3DGS) into the temporal domain, enabling real-time rendering of dynamic scenes. However, one of the major remaining…
Recent advancements in neural visual geometry, including transformer-based models such as VGGT and Pi3, have achieved impressive accuracy on 3D reconstruction tasks. However, their reliance on full attention makes them fundamentally limited…
Recent advancements in Large Vision-Language Models built upon Large Language Models have established aligning visual features with LLM representations as the dominant paradigm. However, inherited LLM architectural designs introduce…
Long-term memory is critical for dialogue systems that support continuous, sustainable, and personalized interactions. However, existing methods rely on continuous summarization or OpenIE-based graph construction paired with fixed…
Autoregressive (AR) video diffusion is a powerful paradigm for streaming and interactive video generation. However, its reliance on softmax self-attention leads to quadratic compute complexity in sequence length and memory usage due to…
Despite recent advancements in the Large Reconstruction Model (LRM) demonstrating impressive results, when extending its input from single image to multiple images, it exhibits inefficiencies, subpar geometric and texture quality, as well…