Related papers: MOSE: Monocular Semantic Reconstruction Using NeRF…
We present a novel method for recovering the absolute pose and shape of a human in a pre-scanned scene given a single image. Unlike previous methods that perform sceneaware mesh optimization, we propose to first estimate absolute position…
Surface reconstruction has traditionally relied on the Multi-View Stereo (MVS)-based pipeline, which often suffers from noisy and incomplete geometry. This is due to that although MVS has been proven to be an effective way to recover the…
Patch-based stereo is nowadays a commonly used image-based technique for dense 3D reconstruction in large scale multi-view applications. The typical steps of such a pipeline can be summarized in stereo pair selection, depth map computation,…
This paper proposes to address the word sense ambiguity issue in an unsupervised manner, where word sense representations are learned along a word sense selection mechanism given contexts. Prior work focused on designing a single model to…
3D object detection from monocular images is an ill-posed problem due to the projective entanglement of depth and scale. To overcome this ambiguity, we present a novel self-supervised method for textured 3D shape reconstruction and pose…
This work proposes a unified self-supervised pre-training framework for transferable multi-modal perception representation learning via masked multi-modal reconstruction in Neural Radiance Field (NeRF), namely NeRF-Supervised Masked…
Multimodal representation learning has shown promising improvements on various vision-language tasks. Most existing methods excel at building global-level alignment between vision and language while lacking effective fine-grained image-text…
Systems which incrementally create 3D semantic maps from image sequences must store and update representations of both geometry and semantic entities. However, while there has been much work on the correct formulation for geometrical…
While deep learning reshaped the classical motion capture pipeline with feed-forward networks, generative models are required to recover fine alignment via iterative refinement. Unfortunately, the existing models are usually hand-crafted or…
Recent advances in neural implicit surfaces for multi-view 3D reconstruction primarily focus on improving large-scale surface reconstruction accuracy, but often produce over-smoothed geometries that lack fine surface details. To address…
Obtaining personalized 3D animatable avatars from a monocular camera has several real world applications in gaming, virtual try-on, animation, and VR/XR, etc. However, it is very challenging to model dynamic and fine-grained clothing…
Neural Radiance Fields (NeRF) have constituted a remarkable breakthrough in image-based 3D reconstruction. However, their implicit volumetric representations differ significantly from the widely-adopted polygonal meshes and lack support…
Monocular depth estimation (MDE) with self-supervised training approaches struggles in low-texture areas, where photometric losses may lead to ambiguous depth predictions. To address this, we propose a novel technique that enhances spatial…
Deep learning on an edge device requires energy efficient operation due to ever diminishing power budget. Intentional low quality data during the data acquisition for longer battery life, and natural noise from the low cost sensor degrade…
Monocular 3D human pose estimation remains a challenging and ill-posed problem, particularly in real-time settings and unconstrained environments. While direct imageto-3D approaches require large annotated datasets and heavy models,…
In 3D object mapping, category-level priors enable efficient object reconstruction and canonical pose estimation, requiring only a single prior per semantic category (e.g., chair, book, laptop, etc.). DeepSDF has been used predominantly as…
Semantic-aware 3D reconstruction from sparse, unposed images remains challenging for feed-forward 3D Gaussian Splatting (3DGS). Existing methods often predict an over-complete set of Gaussian primitives under sparse-view supervision,…
Effectively parsing the facade is essential to 3D building reconstruction, which is an important computer vision problem with a large amount of applications in high precision map for navigation, computer aided design, and city generation…
Neural rendering can be used to reconstruct implicit representations of shapes without 3D supervision. However, current neural surface reconstruction methods have difficulty learning high-frequency geometry details, so the reconstructed…
Neural rendering of implicit surfaces performs well in 3D vision applications. However, it requires dense input views as supervision. When only sparse input images are available, output quality drops significantly due to the shape-radiance…