Result details - ETH3D

Submitted anonymously.

Submission data

Full name	Temporal-AwareDepthFusion
Description	A temporal depth fusion approach that combines stereo-derived depth maps across consecutive frames to improve scene reconstruction and localization. The system uses motion-compensated depth aggregation, confidence-based filtering, and inertial guidance to produce stable depth estimates in dynamic and low-light environments. Global optimization is applied to reduce drift and maintain long-term consistency.
Parameters	Depth fusion window: 12 frames Depth confidence threshold: 0.70 Motion compensation iterations: 8 Keyframe overlap ratio: 0.65 Global optimization interval: 50 frames IMU influence factor: 0.30
Programming language(s)	C++, Python, CUDA
Hardware	A100
Submission creation date	24 Jun, 2026
Last edited	24 Jun, 2026

High-res multi-view results

Info	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.
No results yet.

Low-res many-view results

Info	all	low-res many-view	indoor	outdoor	delivery area	electro	forest	playground	terrains
No results yet.

Low-res two-view results

Info	all	lakes. 1l	lakes. 1s	sand box 1l	sand box 1s	stora. room 1l	stora. room 1s	stora. room 2l	stora. room 2s	stora. room 2 1l	stora. room 2 1s	stora. room 2 2l	stora. room 2 2s	stora. room 3l	stora. room 3s	tunnel 1l	tunnel 1s	tunnel 2l	tunnel 2s	tunnel 3l	tunnel 3s
							0.97	7.05	8.36	9.68	3.62	5.25	3.20	5.72	0.55	0.00	0.00	0.00	0.00	0.06

SLAM results

		all	boxes	boxes dark	buddha	cables 4	cables 5	desk 1	desk 2	desk changing 2	desk dark 1	desk dark 2	desk global light changes	desk ir light	dino	drone	foreground occlusion	helmet	kidnap 2	lamp	large loop 2	large loop 3	large non loop	motion 2	motion 3	motion 4	planar 1	reflective 2	scale change	table 1	table 2	table 5	table 6	table global light changes	table local light changes	table scene	trashbin
	Method	Info
No results yet.