546 citations · 1.1k across the 29 of their papers we have counts for
34 papers
Frequency-Decomposed Avatar Representation for Varying Camera Distances
David Svitov, Pietro Morerio, Lourdes Agapito +1
We present a CloseUpAvatar - a novel approach for articulated human avatar representation supporting a wider range of camera motions, while preserving rendering quality for close-u…
Unsupervised 2D-3D lifting of non-rigid objects using local constraints
Shalini Maiti, Lourdes Agapito, Benjamin Graham
For non-rigid objects, predicting the 3D shape from 2D keypoint observations is ill-posed due to occlusions, and the need to disentangle changes in viewpoint and changes in shape.…
Gen3DEval: Using vLLMs for Automatic Evaluation of Generated 3D Objects
Shalini Maiti, Lourdes Agapito, Filippos Kokkinos
Rapid advancements in text-to-3D generation require robust and scalable evaluation metrics that align closely with human judgment, a need unmet by current metrics such as PSNR and…
BillBoard Splatting (BBSplat): Learnable Textured Primitives for Novel View Synthesis
David Svitov, Pietro Morerio, Lourdes Agapito +1
We present billboard Splatting (BBSplat) - a novel approach for novel view synthesis based on textured geometric primitives. BBSplat represents the scene as a set of optimizable te…
HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Prior
David Svitov, Pietro Morerio, Lourdes Agapito +1
We present HAHA - a novel approach for animatable human avatar generation from monocular input videos. The proposed method relies on learning the trade-off between the use of Gauss…
Task-guided Domain Gap Reduction for Monocular Depth Prediction in Endoscopy
Anita Rau, Binod Bhattarai, Lourdes Agapito +1
Colorectal cancer remains one of the deadliest cancers in the world. In recent years computer-aided methods have aimed to enhance cancer screening and improve the quality and avail…
RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitation
Mel Vecerik, Carl Doersch, Yi Yang +6
For robots to be useful outside labs and specialized factories we need a way to teach them new useful behaviors quickly. Current approaches lack either the generality to onboard ne…
SeMLaPS: Real-time Semantic Mapping with Latent Prior Networks and Quasi-Planar Segmentation
Jingwen Wang, Juan Tarrio, Lourdes Agapito +2
The availability of real-time semantics greatly improves the core geometric functionality of SLAM systems, enabling numerous robotic and AR/VR applications. We present a new method…
HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion
Mustafa Işık, Martin Rünz, Markos Georgopoulos +4
Representing human performance at high-fidelity is an essential building block in diverse applications, such as film production, computer games or videoconferencing. To close the g…
Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM
Hengyi Wang, Jingwen Wang, Lourdes Agapito
We present Co-SLAM, a neural RGB-D SLAM system based on a hybrid representation, that performs robust camera tracking and high-fidelity surface reconstruction in real time. Co-SLAM…
Learning Neural Parametric Head Models
Simon Giebenhain, Tobias Kirschstein, Markos Georgopoulos +3
We propose a novel 3D morphable model for complete human heads based on hybrid neural fields. At the core of our model lies a neural parametric representation that disentangles ide…
GNPM: Geometric-Aware Neural Parametric Models
Mirgahney Mohamed, Lourdes Agapito
We propose Geometric Neural Parametric Models (GNPM), a learned parametric model that takes into account the local structure of data to learn disentangled shape and pose latent spa…
One-Shot Transfer of Affordance Regions? AffCorrs!
Denis Hadjivelichkov, Sicelukwanda Zwane, Marc Peter Deisenroth +2
In this work, we tackle one-shot visual search of object parts. Given a single reference image of an object with annotated affordance regions, we segment semantically corresponding…
GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstruction
Jingwen Wang, Tymoteusz Bleja, Lourdes Agapito
We present GO-Surf, a direct feature grid optimization method for accurate and fast surface reconstruction from RGB-D sequences. We model the underlying scene with a learned hierar…
Bimodal Camera Pose Prediction for Endoscopy
Anita Rau, Binod Bhattarai, Lourdes Agapito +1
Deducing the 3D structure of endoscopic scenes from images is exceedingly challenging. In addition to deformation and view-dependent lighting, tubular structures like the colon pre…
Few-Shot Keypoint Detection as Task Adaptation via Latent Embeddings
Mel Vecerik, Jackie Kay, Raia Hadsell +2
Dense object tracking, the ability to localize specific object points with pixel-level accuracy, is an important computer vision task with numerous downstream applications in robot…
CodeNeRF: Disentangled Neural Radiance Fields for Object Categories
Wonbong Jang, Lourdes Agapito
CodeNeRF is an implicit 3D neural representation that learns the variation of object shapes and textures across a category and can be trained, from a set of posed images, to synthe…
DSP-SLAM: Object Oriented SLAM with Deep Shape Priors
Jingwen Wang, Martin Rünz, Lourdes Agapito
We propose DSP-SLAM, an object-oriented SLAM system that builds a rich and accurate joint map of dense 3D models for foreground objects, and sparse landmark points to represent the…
Multi-person Implicit Reconstruction from a Single Image
Armin Mustafa, Akin Caliskan, Lourdes Agapito +1
We present a new end-to-end learning framework to obtain detailed and spatially coherent reconstructions of multiple people from a single image. Existing multi-person methods suffe…
SelfPose: 3D Egocentric Pose Estimation from a Headset Mounted Camera
Denis Tome, Thiemo Alldieck, Patrick Peluse +4
We present a solution to egocentric 3D body pose estimation from monocular images captured from downward looking fish-eye cameras installed on the rim of a head mounted VR device.…
S3K: Self-Supervised Semantic Keypoints for Robotic Manipulation via Multi-View Consistency
Mel Vecerik, Jean-Baptiste Regli, Oleg Sushkov +7
A robot's ability to act is fundamentally constrained by what it can perceive. Many existing approaches to visual representation learning utilize general-purpose training criteria,…
DiverseNet: When One Right Answer is not Enough
Michael Firman, Neill D. F. Campbell, Lourdes Agapito +1
Many structured prediction tasks in machine vision have a collection of acceptable answers, instead of one definitive ground truth answer. Segmentation of images, for example, is s…
FroDO: From Detections to 3D Objects
Kejie Li, Martin Rünz, Meng Tang +8
Object-oriented maps are important for scene understanding since they jointly capture geometry and semantics, allow individual instantiation and meaningful reasoning about objects.…
xR-EgoPose: Egocentric 3D Human Pose from an HMD Camera
Denis Tome, Patrick Peluse, Lourdes Agapito +1
We present a new solution to egocentric 3D body pose estimation from monocular images captured from a downward looking fish-eye camera installed on the rim of a head mounted virtua…